Token | they |
Token ID | 484 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
oved | +0.036 |
zed | +0.035 |
opes | +0.034 |
ths | +0.031 |
iously | +0.031 |
Neg logit contributions | |
ulu | -0.054 |
J | -0.053 |
ory | -0.052 |
Jill | -0.050 |
common | -0.050 |
Token | had |
Token ID | 550 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
oved | +0.033 |
zed | +0.032 |
opes | +0.032 |
ths | +0.029 |
sed | +0.029 |
Neg logit contributions | |
ulu | -0.033 |
J | -0.031 |
ory | -0.031 |
common | -0.029 |
Jill | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
oved | +0.012 |
zed | +0.012 |
opes | +0.011 |
sed | +0.011 |
ths | +0.011 |
Neg logit contributions | |
ulu | -0.011 |
ory | -0.011 |
J | -0.011 |
ola | -0.010 |
ora | -0.010 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
sed | +0.002 |
ow | +0.002 |
opes | +0.002 |
zed | +0.002 |
oved | +0.002 |
Neg logit contributions | |
ulu | -0.002 |
J | -0.002 |
ill | -0.002 |
ola | -0.002 |
Jill | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ory | +0.049 |
ulu | +0.048 |
J | +0.047 |
emo | +0.045 |
Col | +0.045 |
Neg logit contributions | |
oved | -0.028 |
about | -0.025 |
der | -0.021 |
chair | -0.021 |
zed | -0.019 |
Token | common |
Token ID | 2219 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
ory | +0.013 |
ulu | +0.012 |
ackers | +0.011 |
va | +0.011 |
J | +0.010 |
Neg logit contributions | |
zed | -0.009 |
oved | -0.009 |
opes | -0.008 |
ow | -0.008 |
meanings | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ulu | +0.173 |
ory | +0.164 |
J | +0.160 |
Jill | +0.145 |
ola | +0.143 |
Neg logit contributions | |
oved | -0.199 |
opes | -0.192 |
zed | -0.183 |
iously | -0.174 |
meanings | -0.169 |
Token | They |
Token ID | 1119 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
ory | +0.006 |
ulu | +0.006 |
guard | +0.005 |
ora | +0.005 |
J | +0.005 |
Neg logit contributions | |
oved | -0.004 |
opes | -0.003 |
sed | -0.003 |
der | -0.003 |
Leave | -0.003 |
Token | liked |
Token ID | 8288 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
opes | +0.002 |
sed | +0.002 |
ths | +0.002 |
Neg logit contributions | |
ulu | -0.003 |
ory | -0.002 |
J | -0.002 |
common | -0.002 |
ola | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ulu | +0.028 |
ory | +0.027 |
J | +0.027 |
ola | +0.025 |
common | +0.024 |
Neg logit contributions | |
opes | -0.025 |
oved | -0.025 |
zed | -0.025 |
ths | -0.024 |
sed | -0.023 |
Token | same |
Token ID | 976 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
opes | +0.010 |
oved | +0.010 |
sed | +0.010 |
ow | +0.010 |
meanings | +0.009 |
Neg logit contributions | |
ulu | -0.011 |
J | -0.011 |
opener | -0.010 |
ola | -0.010 |
ory | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
oved | +0.020 |
zed | +0.020 |
opes | +0.020 |
ths | +0.019 |
iously | +0.019 |
Neg logit contributions | |
ory | -0.016 |
J | -0.016 |
ulu | -0.016 |
common | -0.014 |
ola | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
oved | +0.032 |
zed | +0.030 |
opes | +0.030 |
ths | +0.028 |
iously | +0.028 |
Neg logit contributions | |
ulu | -0.035 |
J | -0.034 |
ory | -0.034 |
common | -0.032 |
Jill | -0.031 |
Token | one |
Token ID | 530 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
oved | +0.004 |
zed | +0.004 |
opes | +0.004 |
ths | +0.004 |
iously | +0.004 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
Jill | -0.003 |
common | -0.003 |
Token | thing |
Token ID | 1517 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
ulu | +0.007 |
ory | +0.006 |
J | +0.006 |
common | +0.006 |
Jill | +0.006 |
Neg logit contributions | |
oved | -0.008 |
zed | -0.008 |
opes | -0.008 |
ths | -0.008 |
iously | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
oved | +0.026 |
zed | +0.025 |
opes | +0.024 |
ths | +0.023 |
iously | +0.023 |
Neg logit contributions | |
ulu | -0.028 |
J | -0.027 |
ory | -0.027 |
Jill | -0.025 |
common | -0.025 |
Token | common |
Token ID | 2219 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
ory | +0.040 |
ulu | +0.037 |
J | +0.035 |
ola | +0.032 |
ackers | +0.031 |
Neg logit contributions | |
zed | -0.043 |
oved | -0.043 |
opes | -0.041 |
meanings | -0.038 |
iously | -0.038 |
Token | : |
Token ID | 25 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ulu | +0.158 |
J | +0.152 |
ory | +0.152 |
common | +0.136 |
Jill | +0.136 |
Neg logit contributions | |
oved | -0.205 |
opes | -0.197 |
zed | -0.195 |
iously | -0.184 |
ths | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ulu | +0.020 |
ory | +0.020 |
J | +0.019 |
common | +0.017 |
ola | +0.017 |
Neg logit contributions | |
oved | -0.019 |
opes | -0.019 |
zed | -0.019 |
ths | -0.017 |
iously | -0.017 |
Token | love |
Token ID | 1842 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ulu | +0.040 |
J | +0.040 |
ory | +0.039 |
ola | +0.036 |
ora | +0.034 |
Neg logit contributions | |
oved | -0.038 |
sed | -0.038 |
opes | -0.037 |
zed | -0.037 |
ow | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ulu | +0.077 |
J | +0.076 |
ory | +0.074 |
common | +0.066 |
ola | +0.064 |
Neg logit contributions | |
oved | -0.084 |
zed | -0.079 |
opes | -0.078 |
iously | -0.073 |
ths | -0.072 |
Token | bright |
Token ID | 6016 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
ulu | +0.013 |
J | +0.013 |
ory | +0.012 |
common | +0.011 |
Jill | +0.011 |
Neg logit contributions | |
oved | -0.015 |
zed | -0.015 |
opes | -0.015 |
ths | -0.014 |
iously | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
oved | +0.052 |
zed | +0.049 |
opes | +0.049 |
iously | +0.046 |
ths | +0.045 |
Neg logit contributions | |
ulu | -0.041 |
J | -0.041 |
ory | -0.040 |
common | -0.036 |
Jill | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
J | +0.024 |
ory | +0.024 |
ulu | +0.024 |
common | +0.021 |
ackers | +0.021 |
Neg logit contributions | |
oved | -0.012 |
opes | -0.011 |
Leave | -0.011 |
sed | -0.011 |
der | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ulu | +0.030 |
J | +0.030 |
ory | +0.030 |
Jill | +0.027 |
common | +0.027 |
Neg logit contributions | |
oved | -0.031 |
zed | -0.029 |
opes | -0.029 |
ths | -0.027 |
iously | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
J | +0.038 |
ory | +0.037 |
ulu | +0.036 |
ola | +0.033 |
ora | +0.033 |
Neg logit contributions | |
oved | -0.031 |
opes | -0.031 |
sed | -0.030 |
zed | -0.029 |
ow | -0.028 |
Token | very |
Token ID | 845 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
sed | +0.003 |
oved | +0.003 |
ow | +0.003 |
opes | +0.003 |
zed | +0.003 |
Neg logit contributions | |
J | -0.004 |
ulu | -0.003 |
ory | -0.003 |
ola | -0.003 |
Jill | -0.003 |
Token | common |
Token ID | 2219 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
J | +0.039 |
ulu | +0.037 |
ill | +0.037 |
ory | +0.036 |
ola | +0.035 |
Neg logit contributions | |
sed | -0.028 |
oved | -0.028 |
zed | -0.026 |
meanings | -0.025 |
ow | -0.024 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
J | +0.158 |
ulu | +0.158 |
ory | +0.156 |
ola | +0.135 |
Jill | +0.133 |
Neg logit contributions | |
oved | -0.190 |
opes | -0.180 |
sed | -0.171 |
zed | -0.168 |
meanings | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
J | +0.009 |
ulu | +0.009 |
ory | +0.009 |
Jill | +0.008 |
common | +0.008 |
Neg logit contributions | |
oved | -0.011 |
zed | -0.010 |
opes | -0.010 |
iously | -0.010 |
sed | -0.010 |
Token | It |
Token ID | 632 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ory | +0.027 |
J | +0.027 |
ulu | +0.027 |
common | +0.024 |
ola | +0.023 |
Neg logit contributions | |
oved | -0.013 |
opes | -0.012 |
Leave | -0.012 |
sed | -0.012 |
zed | -0.011 |
Token | likes |
Token ID | 7832 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ulu | +0.035 |
J | +0.034 |
ory | +0.034 |
Jill | +0.031 |
common | +0.031 |
Neg logit contributions | |
oved | -0.037 |
zed | -0.036 |
opes | -0.036 |
ths | -0.033 |
iously | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ulu | +0.053 |
J | +0.051 |
ory | +0.051 |
common | +0.047 |
Jill | +0.047 |
Neg logit contributions | |
oved | -0.053 |
zed | -0.051 |
opes | -0.050 |
ths | -0.047 |
iously | -0.047 |
Token | you |
Token ID | 345 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.022 |
opes | +0.022 |
ths | +0.021 |
iously | +0.021 |
Neg logit contributions | |
ulu | -0.015 |
J | -0.015 |
ory | -0.015 |
Jill | -0.013 |
common | -0.013 |
Token | may |
Token ID | 743 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
ulu | +0.036 |
ory | +0.035 |
J | +0.033 |
common | +0.032 |
Jill | +0.031 |
Neg logit contributions | |
oved | -0.056 |
zed | -0.054 |
opes | -0.054 |
ths | -0.051 |
iously | -0.051 |
Token | find |
Token ID | 1064 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
J | +0.024 |
ulu | +0.023 |
ory | +0.023 |
Jill | +0.021 |
ola | +0.020 |
Neg logit contributions | |
oved | -0.026 |
zed | -0.026 |
opes | -0.025 |
ths | -0.023 |
iously | -0.023 |
Token | something |
Token ID | 1223 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
ulu | +0.004 |
J | +0.004 |
ory | +0.004 |
common | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
oved | -0.006 |
zed | -0.005 |
opes | -0.005 |
ths | -0.005 |
iously | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ulu | +0.018 |
J | +0.017 |
ory | +0.017 |
common | +0.016 |
Jill | +0.016 |
Neg logit contributions | |
oved | -0.023 |
zed | -0.022 |
opes | -0.022 |
ths | -0.021 |
iously | -0.020 |
Token | common |
Token ID | 2219 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
ulu | +0.014 |
ory | +0.014 |
J | +0.014 |
ola | +0.012 |
ora | +0.012 |
Neg logit contributions | |
oved | -0.015 |
zed | -0.014 |
opes | -0.014 |
ths | -0.013 |
meanings | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
ulu | +0.152 |
J | +0.148 |
ory | +0.146 |
Jill | +0.132 |
common | +0.131 |
Neg logit contributions | |
oved | -0.199 |
zed | -0.191 |
opes | -0.191 |
iously | -0.178 |
ths | -0.178 |
Token | This |
Token ID | 770 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
oved | +0.020 |
zed | +0.019 |
opes | +0.018 |
Leave | +0.017 |
ths | +0.017 |
Neg logit contributions | |
ulu | -0.024 |
ory | -0.024 |
J | -0.023 |
common | -0.022 |
mer | -0.021 |
Token | can |
Token ID | 460 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
common | +0.001 |
Jill | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | make |
Token ID | 787 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ulu | +0.029 |
J | +0.028 |
ory | +0.027 |
common | +0.025 |
Jill | +0.025 |
Neg logit contributions | |
oved | -0.042 |
zed | -0.040 |
opes | -0.040 |
ths | -0.038 |
iously | -0.038 |
Token | even |
Token ID | 772 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
oved | +0.010 |
zed | +0.009 |
opes | +0.009 |
ths | +0.009 |
iously | +0.009 |
Neg logit contributions | |
ulu | -0.007 |
ory | -0.007 |
J | -0.007 |
common | -0.006 |
Jill | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ory | +0.032 |
ulu | +0.031 |
J | +0.029 |
ora | +0.026 |
common | +0.026 |
Neg logit contributions | |
oved | -0.041 |
zed | -0.041 |
opes | -0.039 |
ths | -0.038 |
sed | -0.037 |
Token | had |
Token ID | 550 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.022 |
opes | +0.022 |
ths | +0.021 |
iously | +0.020 |
Neg logit contributions | |
ulu | -0.023 |
J | -0.022 |
ory | -0.022 |
common | -0.021 |
Jill | -0.020 |
Token | many |
Token ID | 867 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
oved | +0.013 |
zed | +0.013 |
opes | +0.013 |
ths | +0.012 |
iously | +0.012 |
Neg logit contributions | |
ulu | -0.011 |
J | -0.011 |
ory | -0.011 |
common | -0.010 |
Jill | -0.010 |
Token | things |
Token ID | 1243 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
oved | +0.010 |
opes | +0.009 |
zed | +0.009 |
ths | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.008 |
J | -0.008 |
ory | -0.008 |
Jill | -0.007 |
common | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.005 |
ths | +0.005 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
ory | -0.006 |
common | -0.005 |
Jill | -0.005 |
Token | common |
Token ID | 2219 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
ory | +0.010 |
ulu | +0.009 |
J | +0.008 |
ola | +0.007 |
ackers | +0.007 |
Neg logit contributions | |
oved | -0.018 |
zed | -0.018 |
opes | -0.017 |
meanings | -0.017 |
about | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ulu | +0.156 |
J | +0.149 |
ory | +0.148 |
Jill | +0.133 |
common | +0.130 |
Neg logit contributions | |
oved | -0.197 |
opes | -0.190 |
zed | -0.186 |
iously | -0.175 |
ths | -0.171 |
Token | They |
Token ID | 1119 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
ory | +0.009 |
ulu | +0.009 |
J | +0.008 |
mer | +0.008 |
shell | +0.008 |
Neg logit contributions | |
oved | -0.006 |
Leave | -0.006 |
opes | -0.006 |
meanings | -0.005 |
Eventually | -0.005 |
Token | started |
Token ID | 2067 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
common | +0.001 |
Jill | +0.001 |
Neg logit contributions | |
oved | -0.001 |
opes | -0.001 |
zed | -0.001 |
sed | -0.001 |
ths | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ulu | +0.011 |
J | +0.011 |
ory | +0.011 |
common | +0.010 |
Jill | +0.010 |
Neg logit contributions | |
oved | -0.008 |
zed | -0.008 |
opes | -0.008 |
ths | -0.007 |
iously | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
oved | +0.014 |
zed | +0.014 |
opes | +0.013 |
meanings | +0.013 |
ze | +0.013 |
Neg logit contributions | |
ulu | -0.015 |
ory | -0.015 |
J | -0.015 |
ola | -0.013 |
emo | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.008 |
opes | +0.008 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
ory | -0.006 |
common | -0.005 |
Jill | -0.005 |
Token | one |
Token ID | 530 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.005 |
ths | +0.005 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.004 |
J | -0.004 |
ory | -0.004 |
Jill | -0.004 |
common | -0.004 |
Token | step |
Token ID | 2239 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ulu | +0.044 |
J | +0.041 |
ory | +0.040 |
Jill | +0.039 |
common | +0.036 |
Neg logit contributions | |
opes | -0.075 |
oved | -0.073 |
zed | -0.072 |
iously | -0.068 |
ths | -0.066 |
Token | at |
Token ID | 379 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
oved | +0.038 |
zed | +0.037 |
opes | +0.036 |
ths | +0.034 |
iously | +0.033 |
Neg logit contributions | |
ulu | -0.039 |
J | -0.038 |
ory | -0.038 |
Jill | -0.035 |
common | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ulu | +0.023 |
ory | +0.023 |
J | +0.022 |
ola | +0.020 |
common | +0.019 |
Neg logit contributions | |
oved | -0.030 |
zed | -0.030 |
opes | -0.029 |
ths | -0.028 |
iously | -0.028 |
Token | time |
Token ID | 640 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
ulu | +0.057 |
ory | +0.055 |
J | +0.054 |
Jill | +0.051 |
common | +0.050 |
Neg logit contributions | |
oved | -0.061 |
zed | -0.059 |
opes | -0.056 |
ths | -0.055 |
iously | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
ulu | +0.147 |
J | +0.143 |
ory | +0.141 |
Jill | +0.131 |
common | +0.129 |
Neg logit contributions | |
oved | -0.199 |
zed | -0.193 |
opes | -0.192 |
ths | -0.180 |
iously | -0.178 |
Token | |
Token ID | 220 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
oved | +0.003 |
zed | +0.003 |
opes | +0.003 |
ths | +0.002 |
iously | +0.002 |
Neg logit contributions | |
ulu | -0.004 |
J | -0.004 |
ory | -0.004 |
Jill | -0.003 |
common | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
oved | +0.068 |
zed | +0.066 |
opes | +0.065 |
ths | +0.063 |
iously | +0.063 |
Neg logit contributions | |
ulu | -0.032 |
J | -0.031 |
ory | -0.030 |
Jill | -0.028 |
common | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ory | +0.009 |
ulu | +0.009 |
J | +0.008 |
common | +0.008 |
Jill | +0.007 |
Neg logit contributions | |
zed | -0.012 |
oved | -0.012 |
opes | -0.011 |
ths | -0.011 |
iously | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ulu | +0.011 |
ory | +0.010 |
J | +0.010 |
Jill | +0.010 |
common | +0.009 |
Neg logit contributions | |
oved | -0.009 |
zed | -0.009 |
opes | -0.009 |
ths | -0.008 |
iously | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
ulu | +0.000 |
ory | +0.000 |
J | +0.000 |
ora | +0.000 |
ola | +0.000 |
Neg logit contributions | |
oved | -0.000 |
opes | -0.000 |
zed | -0.000 |
sed | -0.000 |
meanings | -0.000 |
Token | have |
Token ID | 423 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ulu | +0.000 |
J | +0.000 |
ory | +0.000 |
Jill | +0.000 |
common | +0.000 |
Neg logit contributions | |
oved | -0.000 |
zed | -0.000 |
opes | -0.000 |
ths | -0.000 |
iously | -0.000 |
Token | many |
Token ID | 867 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
ulu | +0.020 |
J | +0.019 |
ory | +0.019 |
common | +0.018 |
Jill | +0.018 |
Neg logit contributions | |
oved | -0.022 |
zed | -0.021 |
opes | -0.021 |
ths | -0.019 |
iously | -0.019 |
Token | things |
Token ID | 1243 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
zed | +0.001 |
oved | +0.001 |
opes | +0.001 |
iously | +0.001 |
sed | +0.001 |
Neg logit contributions | |
J | -0.001 |
ulu | -0.001 |
common | -0.001 |
ory | -0.001 |
Jill | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
opes | +0.002 |
ths | +0.002 |
iously | +0.002 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.002 |
ory | -0.002 |
common | -0.002 |
Jill | -0.002 |
Token | common |
Token ID | 2219 |
Feature activation | +5.11e+00 |
Pos logit contributions | |
ory | +0.023 |
ulu | +0.021 |
J | +0.018 |
ora | +0.017 |
ackers | +0.017 |
Neg logit contributions | |
oved | -0.033 |
zed | -0.032 |
opes | -0.031 |
meanings | -0.030 |
ths | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ulu | +0.151 |
ory | +0.144 |
J | +0.143 |
Jill | +0.129 |
common | +0.128 |
Neg logit contributions | |
oved | -0.197 |
opes | -0.189 |
zed | -0.188 |
iously | -0.176 |
ths | -0.174 |
Token | They |
Token ID | 1119 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ulu | +0.002 |
ory | +0.002 |
J | +0.001 |
ora | +0.001 |
mer | +0.001 |
Neg logit contributions | |
oved | -0.001 |
opes | -0.001 |
Leave | -0.001 |
zed | -0.001 |
meanings | -0.001 |
Token | like |
Token ID | 588 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ulu | +0.004 |
J | +0.004 |
ory | +0.004 |
Jill | +0.003 |
common | +0.003 |
Neg logit contributions | |
oved | -0.005 |
opes | -0.005 |
zed | -0.005 |
ths | -0.005 |
meanings | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
ulu | +0.047 |
J | +0.046 |
ory | +0.045 |
Jill | +0.042 |
common | +0.042 |
Neg logit contributions | |
oved | -0.047 |
zed | -0.046 |
opes | -0.045 |
ths | -0.042 |
iously | -0.042 |
Token | same |
Token ID | 976 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
iously | -0.001 |
ths | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
oved | +0.009 |
Leave | +0.009 |
opes | +0.009 |
zed | +0.009 |
sed | +0.008 |
Neg logit contributions | |
ory | -0.014 |
ulu | -0.013 |
J | -0.012 |
ora | -0.012 |
ola | -0.012 |
Token | have |
Token ID | 423 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
oved | +0.017 |
opes | +0.017 |
zed | +0.017 |
meanings | +0.016 |
sed | +0.015 |
Neg logit contributions | |
J | -0.016 |
ulu | -0.016 |
ory | -0.015 |
Jill | -0.014 |
ola | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
oved | +0.004 |
zed | +0.003 |
opes | +0.003 |
iously | +0.003 |
ths | +0.003 |
Neg logit contributions | |
J | -0.002 |
ulu | -0.002 |
Jill | -0.002 |
ory | -0.002 |
common | -0.002 |
Token | lot |
Token ID | 1256 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
sed | +0.016 |
oved | +0.015 |
zed | +0.014 |
ow | +0.014 |
meanings | +0.013 |
Neg logit contributions | |
ulu | -0.024 |
ola | -0.023 |
ory | -0.023 |
J | -0.023 |
ill | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
ory | +0.029 |
ulu | +0.029 |
J | +0.027 |
Nina | +0.026 |
ora | +0.026 |
Neg logit contributions | |
oved | -0.022 |
zed | -0.018 |
der | -0.018 |
opes | -0.018 |
chair | -0.018 |
Token | common |
Token ID | 2219 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
ory | +0.016 |
ulu | +0.015 |
ola | +0.013 |
ora | +0.013 |
va | +0.013 |
Neg logit contributions | |
oved | -0.012 |
opes | -0.012 |
zed | -0.012 |
ow | -0.011 |
meanings | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ulu | +0.148 |
ory | +0.142 |
J | +0.140 |
Jill | +0.127 |
common | +0.124 |
Neg logit contributions | |
oved | -0.196 |
opes | -0.188 |
zed | -0.187 |
iously | -0.174 |
ths | -0.173 |
Token | They |
Token ID | 1119 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
oved | +0.005 |
opes | +0.005 |
Leave | +0.005 |
sed | +0.005 |
meanings | +0.005 |
Neg logit contributions | |
ory | -0.007 |
ulu | -0.007 |
ora | -0.007 |
J | -0.007 |
ola | -0.006 |
Token | become |
Token ID | 1716 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
oved | +0.005 |
opes | +0.005 |
zed | +0.005 |
meanings | +0.005 |
sed | +0.005 |
Neg logit contributions | |
J | -0.005 |
ulu | -0.005 |
ory | -0.005 |
Jill | -0.004 |
ola | -0.004 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ulu | +0.035 |
ory | +0.034 |
J | +0.033 |
ola | +0.032 |
va | +0.031 |
Neg logit contributions | |
oved | -0.019 |
opes | -0.019 |
aged | -0.018 |
muscles | -0.017 |
ths | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.007 |
opes | +0.007 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
common | -0.005 |
Jill | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | searched |
Token ID | 16499 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
ulu | +0.007 |
J | +0.007 |
ory | +0.007 |
common | +0.006 |
Jill | +0.006 |
Neg logit contributions | |
oved | -0.009 |
zed | -0.009 |
opes | -0.009 |
ths | -0.008 |
iously | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ulu | +0.023 |
J | +0.022 |
ory | +0.022 |
ola | +0.020 |
common | +0.020 |
Neg logit contributions | |
oved | -0.021 |
zed | -0.020 |
opes | -0.020 |
iously | -0.019 |
ths | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
zed | +0.018 |
oved | +0.017 |
iously | +0.017 |
opes | +0.017 |
ow | +0.016 |
Neg logit contributions | |
ory | -0.018 |
ulu | -0.018 |
ora | -0.017 |
J | -0.017 |
common | -0.016 |
Token | long |
Token ID | 890 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
ulu | +0.046 |
J | +0.045 |
ory | +0.044 |
Jill | +0.044 |
ola | +0.042 |
Neg logit contributions | |
zed | -0.038 |
oved | -0.037 |
sed | -0.037 |
ze | -0.036 |
Days | -0.035 |
Token | time |
Token ID | 640 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
ulu | +0.021 |
J | +0.021 |
ory | +0.021 |
ola | +0.020 |
Av | +0.019 |
Neg logit contributions | |
zed | -0.019 |
oved | -0.018 |
opes | -0.016 |
iously | -0.016 |
sed | -0.015 |
Token | but |
Token ID | 475 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ulu | +0.168 |
ory | +0.164 |
J | +0.161 |
common | +0.152 |
ora | +0.144 |
Neg logit contributions | |
oved | -0.171 |
zed | -0.162 |
opes | -0.159 |
iously | -0.154 |
ths | -0.149 |
Token | he |
Token ID | 339 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
ulu | +0.007 |
ory | +0.007 |
J | +0.007 |
common | +0.007 |
Jill | +0.006 |
Neg logit contributions | |
oved | -0.009 |
zed | -0.009 |
opes | -0.008 |
ths | -0.008 |
iously | -0.008 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
oved | +0.017 |
zed | +0.017 |
opes | +0.016 |
ths | +0.015 |
iously | +0.015 |
Neg logit contributions | |
ulu | -0.025 |
J | -0.025 |
ory | -0.025 |
common | -0.023 |
Jill | -0.023 |
Token | 't |
Token ID | 470 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
oved | +0.041 |
zed | +0.039 |
opes | +0.039 |
ths | +0.036 |
iously | +0.036 |
Neg logit contributions | |
ulu | -0.055 |
J | -0.054 |
ory | -0.054 |
common | -0.050 |
Jill | -0.050 |
Token | find |
Token ID | 1064 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ulu | +0.045 |
J | +0.044 |
ory | +0.044 |
common | +0.041 |
Jill | +0.039 |
Neg logit contributions | |
oved | -0.066 |
zed | -0.064 |
opes | -0.060 |
iously | -0.060 |
ths | -0.057 |
Token | up |
Token ID | 510 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ory | +0.008 |
ulu | +0.008 |
J | +0.008 |
ackers | +0.008 |
rust | +0.007 |
Neg logit contributions | |
zed | -0.005 |
oved | -0.005 |
erved | -0.005 |
iously | -0.005 |
ths | -0.004 |
Token | one |
Token ID | 530 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
oved | +0.017 |
zed | +0.017 |
opes | +0.016 |
iously | +0.016 |
ths | +0.016 |
Neg logit contributions | |
ulu | -0.018 |
ory | -0.018 |
J | -0.017 |
ola | -0.016 |
common | -0.015 |
Token | step |
Token ID | 2239 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ulu | +0.048 |
ory | +0.047 |
J | +0.047 |
common | +0.043 |
Jill | +0.041 |
Neg logit contributions | |
oved | -0.066 |
zed | -0.062 |
ths | -0.060 |
opes | -0.059 |
iously | -0.058 |
Token | at |
Token ID | 379 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
oved | +0.035 |
zed | +0.032 |
iously | +0.031 |
ths | +0.030 |
opes | +0.029 |
Neg logit contributions | |
ulu | -0.043 |
common | -0.042 |
ory | -0.042 |
J | -0.041 |
Jill | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ulu | +0.015 |
ory | +0.015 |
J | +0.014 |
ora | +0.013 |
ola | +0.013 |
Neg logit contributions | |
oved | -0.018 |
zed | -0.018 |
opes | -0.018 |
iously | -0.017 |
ths | -0.017 |
Token | time |
Token ID | 640 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
ulu | +0.058 |
ory | +0.056 |
J | +0.055 |
Jill | +0.050 |
ola | +0.050 |
Neg logit contributions | |
oved | -0.058 |
zed | -0.057 |
opes | -0.054 |
ths | -0.053 |
ze | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ulu | +0.142 |
J | +0.138 |
ory | +0.136 |
Jill | +0.126 |
common | +0.125 |
Neg logit contributions | |
oved | -0.195 |
zed | -0.190 |
opes | -0.188 |
ths | -0.178 |
iously | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
ulu | +0.008 |
J | +0.008 |
ory | +0.008 |
Jill | +0.007 |
common | +0.007 |
Neg logit contributions | |
oved | -0.009 |
zed | -0.009 |
opes | -0.009 |
ths | -0.008 |
iously | -0.008 |
Token | slowly |
Token ID | 6364 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ulu | +0.019 |
J | +0.019 |
ory | +0.018 |
Jill | +0.018 |
common | +0.017 |
Neg logit contributions | |
oved | -0.026 |
opes | -0.025 |
zed | -0.025 |
iously | -0.023 |
ths | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
oved | +0.038 |
zed | +0.037 |
opes | +0.036 |
ths | +0.035 |
iously | +0.035 |
Neg logit contributions | |
ulu | -0.032 |
ory | -0.031 |
J | -0.031 |
common | -0.028 |
Jill | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
oved | +0.009 |
opes | +0.009 |
zed | +0.009 |
ths | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.008 |
J | -0.008 |
ory | -0.007 |
Jill | -0.007 |
common | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
oved | +0.022 |
opes | +0.022 |
zed | +0.021 |
ths | +0.020 |
iously | +0.020 |
Neg logit contributions | |
ulu | -0.016 |
ory | -0.015 |
J | -0.015 |
Jill | -0.014 |
common | -0.014 |
Token | lots |
Token ID | 6041 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
oved | +0.007 |
zed | +0.007 |
opes | +0.007 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.007 |
J | -0.006 |
ory | -0.006 |
common | -0.006 |
Jill | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
oved | +0.017 |
zed | +0.016 |
opes | +0.016 |
ths | +0.015 |
iously | +0.015 |
Neg logit contributions | |
ulu | -0.013 |
J | -0.013 |
ory | -0.013 |
common | -0.012 |
Jill | -0.012 |
Token | things |
Token ID | 1243 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.008 |
opes | +0.008 |
meanings | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.008 |
ory | -0.008 |
J | -0.008 |
ora | -0.007 |
Jill | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
ulu | +0.002 |
J | +0.002 |
ory | +0.002 |
common | +0.001 |
Jill | +0.001 |
Neg logit contributions | |
oved | -0.002 |
zed | -0.002 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | common |
Token ID | 2219 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
ulu | +0.024 |
ory | +0.024 |
J | +0.021 |
ora | +0.020 |
ola | +0.019 |
Neg logit contributions | |
zed | -0.028 |
oved | -0.027 |
opes | -0.025 |
ths | -0.024 |
meanings | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
ulu | +0.148 |
J | +0.141 |
ory | +0.140 |
common | +0.127 |
Jill | +0.127 |
Neg logit contributions | |
oved | -0.193 |
zed | -0.185 |
opes | -0.184 |
iously | -0.172 |
ths | -0.171 |
Token | like |
Token ID | 588 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ulu | +0.027 |
ory | +0.026 |
J | +0.026 |
common | +0.024 |
ola | +0.023 |
Neg logit contributions | |
oved | -0.029 |
zed | -0.028 |
opes | -0.027 |
iously | -0.025 |
ths | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
ulu | +0.066 |
ory | +0.064 |
J | +0.063 |
common | +0.058 |
Jill | +0.056 |
Neg logit contributions | |
oved | -0.075 |
zed | -0.073 |
opes | -0.071 |
ths | -0.067 |
iously | -0.067 |
Token | love |
Token ID | 1842 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
oved | +0.026 |
zed | +0.025 |
opes | +0.025 |
sed | +0.023 |
iously | +0.023 |
Neg logit contributions | |
ulu | -0.025 |
J | -0.024 |
ory | -0.024 |
Jill | -0.022 |
common | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ulu | +0.054 |
J | +0.052 |
ory | +0.051 |
common | +0.047 |
Jill | +0.046 |
Neg logit contributions | |
oved | -0.063 |
zed | -0.061 |
opes | -0.059 |
ths | -0.056 |
iously | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
oved | +0.042 |
zed | +0.042 |
iously | +0.041 |
ths | +0.040 |
opes | +0.038 |
Neg logit contributions | |
ory | -0.052 |
ulu | -0.048 |
ackers | -0.046 |
J | -0.045 |
emo | -0.044 |
Token | one |
Token ID | 530 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
opes | +0.002 |
ths | +0.002 |
iously | +0.002 |
Neg logit contributions | |
ulu | -0.002 |
J | -0.002 |
ory | -0.002 |
Jill | -0.002 |
common | -0.002 |
Token | step |
Token ID | 2239 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ulu | +0.052 |
ory | +0.051 |
J | +0.051 |
common | +0.046 |
Jill | +0.045 |
Neg logit contributions | |
oved | -0.072 |
zed | -0.069 |
opes | -0.068 |
ths | -0.065 |
iously | -0.065 |
Token | at |
Token ID | 379 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
oved | +0.034 |
zed | +0.033 |
opes | +0.031 |
iously | +0.031 |
ths | +0.031 |
Neg logit contributions | |
ulu | -0.037 |
ory | -0.036 |
J | -0.035 |
common | -0.035 |
Jill | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ory | +0.024 |
ulu | +0.023 |
J | +0.022 |
ola | +0.021 |
common | +0.020 |
Neg logit contributions | |
zed | -0.024 |
oved | -0.023 |
opes | -0.023 |
iously | -0.022 |
ths | -0.022 |
Token | time |
Token ID | 640 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
ulu | +0.054 |
ory | +0.054 |
J | +0.052 |
ola | +0.049 |
Jill | +0.049 |
Neg logit contributions | |
oved | -0.052 |
zed | -0.052 |
opes | -0.049 |
ow | -0.047 |
ze | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ulu | +0.143 |
J | +0.138 |
ory | +0.137 |
common | +0.125 |
Jill | +0.125 |
Neg logit contributions | |
oved | -0.193 |
zed | -0.187 |
opes | -0.185 |
ths | -0.175 |
iously | -0.174 |
Token |
|
Token ID | 198 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ulu | +0.013 |
ory | +0.012 |
J | +0.012 |
common | +0.011 |
Jill | +0.011 |
Neg logit contributions | |
oved | -0.015 |
zed | -0.015 |
opes | -0.015 |
ths | -0.014 |
iously | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ory | +0.014 |
ulu | +0.013 |
J | +0.012 |
common | +0.012 |
Jill | +0.012 |
Neg logit contributions | |
zed | -0.017 |
oved | -0.017 |
opes | -0.016 |
ths | -0.015 |
aged | -0.015 |
Token | Their |
Token ID | 14574 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ory | +0.016 |
ulu | +0.015 |
J | +0.014 |
Jill | +0.014 |
common | +0.014 |
Neg logit contributions | |
zed | -0.014 |
oved | -0.014 |
opes | -0.013 |
ths | -0.013 |
erved | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
oved | +0.033 |
zed | +0.032 |
opes | +0.031 |
iously | +0.030 |
ths | +0.029 |
Neg logit contributions | |
J | -0.015 |
ulu | -0.014 |
ory | -0.014 |
Jill | -0.014 |
common | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
oved | +0.019 |
zed | +0.019 |
opes | +0.019 |
ths | +0.018 |
iously | +0.018 |
Neg logit contributions | |
ulu | -0.012 |
J | -0.011 |
ory | -0.011 |
common | -0.010 |
Jill | -0.010 |
Token | books |
Token ID | 3835 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
J | +0.019 |
ory | +0.017 |
ulu | +0.017 |
Jill | +0.017 |
common | +0.017 |
Neg logit contributions | |
zed | -0.023 |
oved | -0.023 |
ths | -0.022 |
opes | -0.022 |
iously | -0.021 |
Token | one |
Token ID | 530 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
opes | +0.013 |
oved | +0.013 |
zed | +0.013 |
sed | +0.012 |
ths | +0.012 |
Neg logit contributions | |
ulu | -0.009 |
J | -0.009 |
ory | -0.008 |
Jill | -0.008 |
common | -0.007 |
Token | at |
Token ID | 379 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ulu | +0.057 |
J | +0.055 |
ory | +0.054 |
Jill | +0.051 |
common | +0.050 |
Neg logit contributions | |
oved | -0.083 |
zed | -0.082 |
opes | -0.081 |
iously | -0.075 |
sed | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ulu | +0.034 |
ory | +0.034 |
J | +0.032 |
common | +0.029 |
ola | +0.028 |
Neg logit contributions | |
oved | -0.047 |
zed | -0.045 |
opes | -0.045 |
ths | -0.043 |
iously | -0.043 |
Token | time |
Token ID | 640 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
ulu | +0.051 |
ory | +0.049 |
J | +0.049 |
common | +0.045 |
Jill | +0.045 |
Neg logit contributions | |
oved | -0.067 |
zed | -0.065 |
opes | -0.064 |
ths | -0.060 |
iously | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ulu | +0.136 |
J | +0.133 |
ory | +0.130 |
Jill | +0.121 |
common | +0.119 |
Neg logit contributions | |
oved | -0.197 |
zed | -0.193 |
opes | -0.190 |
ths | -0.180 |
iously | -0.178 |
Token | In |
Token ID | 554 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.005 |
ths | +0.004 |
iously | +0.004 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
Jill | -0.006 |
ory | -0.006 |
Jenny | -0.006 |
Token | each |
Token ID | 1123 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ulu | +0.024 |
ory | +0.023 |
J | +0.023 |
common | +0.020 |
Jill | +0.020 |
Neg logit contributions | |
oved | -0.040 |
zed | -0.039 |
opes | -0.038 |
ths | -0.036 |
iously | -0.036 |
Token | book |
Token ID | 1492 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.008 |
opes | +0.007 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
common | -0.004 |
Jill | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ulu | +0.005 |
J | +0.005 |
Jill | +0.005 |
ory | +0.005 |
common | +0.005 |
Neg logit contributions | |
oved | -0.008 |
zed | -0.008 |
opes | -0.008 |
iously | -0.008 |
ths | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
oved | +0.030 |
opes | +0.029 |
zed | +0.029 |
ths | +0.028 |
iously | +0.028 |
Neg logit contributions | |
ulu | -0.021 |
ory | -0.020 |
J | -0.020 |
Jill | -0.019 |
common | -0.018 |
Token | lots |
Token ID | 6041 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.005 |
ths | +0.005 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
common | -0.004 |
Jill | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
oved | +0.020 |
zed | +0.019 |
opes | +0.019 |
ths | +0.018 |
iously | +0.018 |
Neg logit contributions | |
ulu | -0.017 |
J | -0.016 |
ory | -0.016 |
common | -0.015 |
Jill | -0.015 |
Token | things |
Token ID | 1243 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
oved | +0.011 |
opes | +0.010 |
zed | +0.010 |
meanings | +0.009 |
iously | +0.009 |
Neg logit contributions | |
ulu | -0.011 |
ory | -0.010 |
J | -0.010 |
ora | -0.009 |
Jill | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
oved | +0.003 |
zed | +0.003 |
opes | +0.003 |
ths | +0.003 |
iously | +0.003 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
common | -0.003 |
Jill | -0.003 |
Token | common |
Token ID | 2219 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
ulu | +0.019 |
ory | +0.019 |
J | +0.016 |
ora | +0.016 |
ola | +0.015 |
Neg logit contributions | |
zed | -0.023 |
oved | -0.023 |
opes | -0.021 |
ths | -0.020 |
meanings | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
ulu | +0.143 |
J | +0.136 |
ory | +0.136 |
common | +0.123 |
Jill | +0.123 |
Neg logit contributions | |
oved | -0.190 |
zed | -0.182 |
opes | -0.181 |
iously | -0.170 |
ths | -0.168 |
Token | like |
Token ID | 588 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ulu | +0.028 |
ory | +0.027 |
J | +0.026 |
common | +0.024 |
ola | +0.024 |
Neg logit contributions | |
oved | -0.029 |
zed | -0.029 |
opes | -0.028 |
iously | -0.026 |
ths | -0.026 |
Token | his |
Token ID | 465 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ulu | +0.060 |
ory | +0.059 |
J | +0.058 |
common | +0.053 |
ora | +0.051 |
Neg logit contributions | |
oved | -0.069 |
zed | -0.067 |
opes | -0.066 |
ths | -0.062 |
iously | -0.061 |
Token | love |
Token ID | 1842 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
oved | +0.036 |
zed | +0.034 |
opes | +0.034 |
sed | +0.031 |
iously | +0.031 |
Neg logit contributions | |
ulu | -0.033 |
J | -0.032 |
ory | -0.031 |
common | -0.029 |
Jill | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ulu | +0.046 |
J | +0.044 |
ory | +0.044 |
common | +0.040 |
Jill | +0.039 |
Neg logit contributions | |
oved | -0.055 |
zed | -0.053 |
opes | -0.052 |
ths | -0.049 |
iously | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
oved | +0.025 |
zed | +0.024 |
opes | +0.024 |
ths | +0.023 |
iously | +0.022 |
Neg logit contributions | |
ulu | -0.017 |
J | -0.016 |
ory | -0.016 |
Jill | -0.015 |
common | -0.015 |
Token | one |
Token ID | 530 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | number |
Token ID | 1271 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
ulu | +0.044 |
Jill | +0.043 |
J | +0.042 |
ory | +0.042 |
common | +0.038 |
Neg logit contributions | |
opes | -0.076 |
zed | -0.075 |
oved | -0.075 |
erved | -0.071 |
sed | -0.069 |
Token | at |
Token ID | 379 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ulu | +0.029 |
J | +0.028 |
ory | +0.028 |
Jill | +0.026 |
common | +0.026 |
Neg logit contributions | |
oved | -0.037 |
zed | -0.036 |
opes | -0.035 |
ths | -0.033 |
iously | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ulu | +0.019 |
ory | +0.019 |
J | +0.018 |
common | +0.017 |
ola | +0.016 |
Neg logit contributions | |
oved | -0.021 |
opes | -0.021 |
zed | -0.020 |
ths | -0.019 |
iously | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
ulu | +0.050 |
J | +0.047 |
ory | +0.047 |
ola | +0.043 |
common | +0.042 |
Neg logit contributions | |
oved | -0.058 |
zed | -0.056 |
opes | -0.054 |
ths | -0.052 |
iously | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ulu | +0.139 |
ory | +0.134 |
J | +0.133 |
common | +0.122 |
Jill | +0.120 |
Neg logit contributions | |
oved | -0.190 |
zed | -0.183 |
opes | -0.181 |
ths | -0.172 |
iously | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ulu | +0.012 |
ory | +0.011 |
J | +0.011 |
common | +0.010 |
ola | +0.010 |
Neg logit contributions | |
oved | -0.011 |
zed | -0.011 |
opes | -0.010 |
iously | -0.010 |
ths | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ory | +0.008 |
ulu | +0.008 |
J | +0.008 |
common | +0.007 |
Jill | +0.007 |
Neg logit contributions | |
oved | -0.012 |
zed | -0.012 |
opes | -0.012 |
ths | -0.011 |
iously | -0.011 |
Token | As |
Token ID | 1722 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ulu | +0.012 |
ory | +0.012 |
J | +0.011 |
Jill | +0.011 |
common | +0.011 |
Neg logit contributions | |
oved | -0.009 |
zed | -0.009 |
opes | -0.009 |
ths | -0.008 |
iously | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ulu | +0.010 |
ory | +0.010 |
ora | +0.009 |
ola | +0.009 |
J | +0.009 |
Neg logit contributions | |
zed | -0.010 |
ths | -0.010 |
oved | -0.009 |
iously | -0.008 |
opes | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
zed | +0.012 |
oved | +0.012 |
opes | +0.012 |
sed | +0.011 |
ths | +0.011 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
Jill | -0.006 |
ory | -0.006 |
common | -0.005 |
Token | one |
Token ID | 530 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
oved | +0.010 |
opes | +0.009 |
zed | +0.009 |
ths | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
ory | -0.006 |
Jill | -0.006 |
common | -0.005 |
Token | step |
Token ID | 2239 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
ulu | +0.044 |
Jill | +0.039 |
J | +0.038 |
deeper | +0.036 |
closer | +0.035 |
Neg logit contributions | |
opes | -0.086 |
zed | -0.084 |
oved | -0.082 |
sed | -0.076 |
erved | -0.075 |
Token | at |
Token ID | 379 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
oved | +0.028 |
zed | +0.028 |
opes | +0.027 |
ths | +0.025 |
iously | +0.025 |
Neg logit contributions | |
ulu | -0.025 |
J | -0.024 |
ory | -0.024 |
Jill | -0.022 |
common | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ory | +0.021 |
ulu | +0.021 |
J | +0.020 |
common | +0.018 |
ola | +0.017 |
Neg logit contributions | |
oved | -0.029 |
zed | -0.028 |
opes | -0.028 |
ths | -0.027 |
iously | -0.027 |
Token | time |
Token ID | 640 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
ulu | +0.048 |
ory | +0.048 |
J | +0.047 |
Jill | +0.043 |
common | +0.043 |
Neg logit contributions | |
oved | -0.056 |
zed | -0.055 |
opes | -0.053 |
ths | -0.051 |
iously | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
ulu | +0.119 |
J | +0.116 |
ory | +0.110 |
Jill | +0.108 |
common | +0.101 |
Neg logit contributions | |
oved | -0.204 |
zed | -0.203 |
opes | -0.202 |
ths | -0.189 |
erved | -0.186 |
Token | They |
Token ID | 1119 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
ulu | +0.000 |
ory | +0.000 |
J | +0.000 |
common | +0.000 |
ola | +0.000 |
Neg logit contributions | |
oved | -0.000 |
zed | -0.000 |
opes | -0.000 |
sed | -0.000 |
iously | -0.000 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
oved | +0.003 |
opes | +0.003 |
zed | +0.003 |
iously | +0.003 |
ths | +0.003 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
Jill | -0.002 |
common | -0.002 |
Token | at |
Token ID | 379 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ulu | +0.000 |
ory | +0.000 |
J | +0.000 |
Jill | +0.000 |
common | +0.000 |
Neg logit contributions | |
oved | -0.000 |
zed | -0.000 |
opes | -0.000 |
ths | -0.000 |
iously | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
oved | +0.020 |
zed | +0.019 |
opes | +0.019 |
ths | +0.018 |
iously | +0.018 |
Neg logit contributions | |
ulu | -0.010 |
J | -0.009 |
ory | -0.009 |
Jill | -0.009 |
common | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.008 |
opes | +0.008 |
iously | +0.007 |
ths | +0.007 |
Neg logit contributions | |
ulu | -0.007 |
ory | -0.007 |
J | -0.006 |
common | -0.006 |
Jill | -0.006 |
Token | one |
Token ID | 530 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
oved | +0.007 |
opes | +0.007 |
zed | +0.006 |
ths | +0.006 |
iously | +0.006 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
Jill | -0.005 |
common | -0.005 |
Token | step |
Token ID | 2239 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ulu | +0.059 |
J | +0.056 |
ory | +0.053 |
Jill | +0.052 |
ola | +0.049 |
Neg logit contributions | |
opes | -0.091 |
oved | -0.090 |
zed | -0.088 |
iously | -0.082 |
sed | -0.082 |
Token | at |
Token ID | 379 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
oved | +0.019 |
zed | +0.019 |
opes | +0.018 |
iously | +0.017 |
ths | +0.017 |
Neg logit contributions | |
ulu | -0.020 |
ory | -0.020 |
J | -0.020 |
common | -0.019 |
Jill | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ory | +0.015 |
ulu | +0.015 |
J | +0.014 |
common | +0.013 |
ola | +0.013 |
Neg logit contributions | |
oved | -0.019 |
zed | -0.019 |
opes | -0.018 |
iously | -0.018 |
ths | -0.018 |
Token | time |
Token ID | 640 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
ulu | +0.040 |
ory | +0.040 |
J | +0.039 |
Jill | +0.036 |
common | +0.035 |
Neg logit contributions | |
oved | -0.043 |
zed | -0.042 |
opes | -0.039 |
ths | -0.039 |
iously | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ulu | +0.136 |
J | +0.132 |
ory | +0.129 |
Jill | +0.121 |
common | +0.118 |
Neg logit contributions | |
oved | -0.189 |
zed | -0.184 |
opes | -0.183 |
ths | -0.172 |
iously | -0.170 |
Token | |
Token ID | 220 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
oved | +0.009 |
zed | +0.008 |
opes | +0.008 |
iously | +0.007 |
ths | +0.007 |
Neg logit contributions | |
ulu | -0.014 |
ory | -0.014 |
J | -0.014 |
common | -0.014 |
ola | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
oved | +0.052 |
zed | +0.050 |
opes | +0.050 |
ths | +0.047 |
iously | +0.047 |
Neg logit contributions | |
ulu | -0.029 |
ory | -0.028 |
J | -0.028 |
common | -0.025 |
Jill | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ory | +0.010 |
ulu | +0.009 |
common | +0.009 |
mer | +0.008 |
shrimp | +0.008 |
Neg logit contributions | |
zed | -0.010 |
oved | -0.010 |
opes | -0.009 |
ths | -0.009 |
ending | -0.009 |
Token | When |
Token ID | 2215 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
ory | +0.011 |
ulu | +0.010 |
common | +0.010 |
Jill | +0.009 |
J | +0.009 |
Neg logit contributions | |
oved | -0.008 |
zed | -0.008 |
ths | -0.007 |
opes | -0.007 |
ending | -0.006 |
Token | One |
Token ID | 1881 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
oved | +0.009 |
zed | +0.009 |
opes | +0.009 |
ths | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.011 |
J | -0.011 |
ory | -0.011 |
common | -0.010 |
Jill | -0.010 |
Token | slow |
Token ID | 3105 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ulu | +0.024 |
J | +0.022 |
ory | +0.021 |
Jill | +0.021 |
common | +0.020 |
Neg logit contributions | |
oved | -0.037 |
opes | -0.037 |
zed | -0.036 |
iously | -0.034 |
sed | -0.034 |
Token | step |
Token ID | 2239 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
ulu | +0.031 |
J | +0.030 |
ory | +0.030 |
common | +0.027 |
Jill | +0.027 |
Neg logit contributions | |
oved | -0.037 |
zed | -0.036 |
opes | -0.036 |
ths | -0.034 |
iously | -0.034 |
Token | at |
Token ID | 379 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
oved | +0.025 |
zed | +0.024 |
opes | +0.023 |
ths | +0.022 |
iously | +0.022 |
Neg logit contributions | |
ulu | -0.030 |
ory | -0.030 |
J | -0.030 |
common | -0.028 |
Jill | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ory | +0.012 |
ulu | +0.012 |
J | +0.012 |
common | +0.011 |
mer | +0.011 |
Neg logit contributions | |
oved | -0.012 |
zed | -0.012 |
ths | -0.012 |
opes | -0.012 |
iously | -0.012 |
Token | time |
Token ID | 640 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ulu | +0.041 |
ory | +0.040 |
J | +0.039 |
common | +0.036 |
Jill | +0.036 |
Neg logit contributions | |
oved | -0.045 |
zed | -0.044 |
ths | -0.042 |
opes | -0.041 |
iously | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ulu | +0.138 |
J | +0.133 |
ory | +0.132 |
Jill | +0.122 |
common | +0.121 |
Neg logit contributions | |
oved | -0.186 |
zed | -0.181 |
opes | -0.179 |
ths | -0.168 |
iously | -0.167 |
Token | she |
Token ID | 673 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ulu | +0.009 |
ory | +0.009 |
J | +0.009 |
common | +0.008 |
ola | +0.008 |
Neg logit contributions | |
oved | -0.011 |
zed | -0.010 |
opes | -0.010 |
ths | -0.010 |
iously | -0.010 |
Token | followed |
Token ID | 3940 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
oved | +0.010 |
zed | +0.010 |
opes | +0.010 |
ths | +0.009 |
iously | +0.009 |
Neg logit contributions | |
ulu | -0.008 |
J | -0.008 |
ory | -0.008 |
Jill | -0.008 |
common | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
zed | +0.022 |
oved | +0.022 |
iously | +0.021 |
ths | +0.020 |
zy | +0.020 |
Neg logit contributions | |
ulu | -0.023 |
ory | -0.022 |
J | -0.021 |
common | -0.020 |
ackers | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
oved | +0.031 |
zed | +0.030 |
opes | +0.030 |
iously | +0.028 |
ths | +0.028 |
Neg logit contributions | |
ulu | -0.020 |
J | -0.019 |
ory | -0.019 |
Jill | -0.018 |
common | -0.018 |
Token | wood |
Token ID | 4898 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
opes | +0.004 |
oved | +0.004 |
zed | +0.004 |
iously | +0.004 |
ths | +0.004 |
Neg logit contributions | |
ory | -0.004 |
ulu | -0.004 |
J | -0.004 |
ola | -0.004 |
common | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
oved | +0.025 |
zed | +0.024 |
opes | +0.023 |
ths | +0.022 |
iously | +0.022 |
Neg logit contributions | |
ulu | -0.020 |
J | -0.019 |
ory | -0.019 |
common | -0.018 |
Jill | -0.017 |
Token | One |
Token ID | 1881 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ulu | +0.003 |
ory | +0.003 |
J | +0.003 |
common | +0.003 |
ora | +0.003 |
Neg logit contributions | |
oved | -0.002 |
zed | -0.002 |
opes | -0.002 |
iously | -0.002 |
ths | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
ulu | +0.037 |
J | +0.035 |
ory | +0.035 |
Jill | +0.032 |
common | +0.032 |
Neg logit contributions | |
oved | -0.059 |
zed | -0.057 |
opes | -0.057 |
iously | -0.054 |
ths | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ulu | +0.027 |
ory | +0.027 |
J | +0.026 |
common | +0.024 |
ola | +0.023 |
Neg logit contributions | |
oved | -0.032 |
zed | -0.031 |
opes | -0.030 |
ths | -0.028 |
iously | -0.028 |
Token | trou |
Token ID | 4057 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
ulu | +0.018 |
J | +0.017 |
ory | +0.017 |
ill | +0.017 |
ola | +0.017 |
Neg logit contributions | |
ths | -0.014 |
sed | -0.014 |
zed | -0.013 |
oved | -0.013 |
ow | -0.013 |
Token | l |
Token ID | 75 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ory | +0.170 |
ulu | +0.161 |
J | +0.155 |
Jill | +0.150 |
common | +0.150 |
Neg logit contributions | |
oved | -0.157 |
zed | -0.144 |
opes | -0.140 |
ths | -0.135 |
iously | -0.130 |
Token | be |
Token ID | 1350 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
zed | +0.017 |
ths | +0.016 |
opes | +0.015 |
iously | +0.015 |
oved | +0.015 |
Neg logit contributions | |
ulu | -0.018 |
J | -0.016 |
ory | -0.016 |
Jill | -0.015 |
ora | -0.015 |
Token | came |
Token ID | 1625 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ulu | +0.058 |
ory | +0.057 |
J | +0.056 |
common | +0.053 |
Jill | +0.052 |
Neg logit contributions | |
oved | -0.051 |
zed | -0.050 |
opes | -0.048 |
iously | -0.045 |
ths | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.008 |
opes | +0.008 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.008 |
J | -0.008 |
ory | -0.008 |
common | -0.007 |
Jill | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
zed | +0.010 |
oved | +0.009 |
opes | +0.009 |
iously | +0.009 |
ths | +0.009 |
Neg logit contributions | |
ulu | -0.009 |
J | -0.009 |
ory | -0.008 |
ola | -0.008 |
ora | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
oved | +0.007 |
zed | +0.006 |
opes | +0.006 |
ths | +0.006 |
iously | +0.006 |
Neg logit contributions | |
ulu | -0.007 |
J | -0.007 |
ory | -0.007 |
Jill | -0.007 |
common | -0.006 |
Token | searched |
Token ID | 16499 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
oved | +0.021 |
zed | +0.021 |
opes | +0.020 |
ths | +0.019 |
iously | +0.019 |
Neg logit contributions | |
ulu | -0.015 |
J | -0.014 |
ory | -0.014 |
common | -0.013 |
Jill | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ulu | +0.001 |
ory | +0.001 |
J | +0.001 |
common | +0.001 |
ola | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
zed | +0.037 |
oved | +0.036 |
opes | +0.035 |
iously | +0.034 |
ths | +0.034 |
Neg logit contributions | |
ory | -0.033 |
ulu | -0.032 |
J | -0.030 |
common | -0.029 |
ora | -0.028 |
Token | long |
Token ID | 890 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ulu | +0.033 |
ory | +0.032 |
J | +0.031 |
Jill | +0.031 |
ola | +0.030 |
Neg logit contributions | |
oved | -0.031 |
zed | -0.030 |
sed | -0.029 |
ths | -0.029 |
opes | -0.029 |
Token | time |
Token ID | 640 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ulu | +0.009 |
J | +0.009 |
ory | +0.009 |
ola | +0.009 |
Jill | +0.008 |
Neg logit contributions | |
oved | -0.010 |
zed | -0.010 |
opes | -0.009 |
ths | -0.009 |
iously | -0.009 |
Token | until |
Token ID | 1566 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
ulu | +0.156 |
ory | +0.154 |
J | +0.150 |
common | +0.142 |
Jill | +0.135 |
Neg logit contributions | |
oved | -0.164 |
zed | -0.155 |
opes | -0.152 |
iously | -0.146 |
ths | -0.145 |
Token | she |
Token ID | 673 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
zed | +0.012 |
oved | +0.011 |
ths | +0.011 |
iously | +0.010 |
opes | +0.010 |
Neg logit contributions | |
ory | -0.011 |
ulu | -0.010 |
J | -0.010 |
common | -0.010 |
ora | -0.009 |
Token | found |
Token ID | 1043 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
zed | +0.037 |
oved | +0.036 |
ths | +0.033 |
opes | +0.031 |
iously | +0.031 |
Neg logit contributions | |
common | -0.035 |
ory | -0.034 |
ulu | -0.033 |
J | -0.032 |
ora | -0.030 |
Token | something |
Token ID | 1223 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ory | +0.004 |
ulu | +0.004 |
J | +0.004 |
common | +0.004 |
ola | +0.003 |
Neg logit contributions | |
oved | -0.005 |
zed | -0.005 |
opes | -0.004 |
iously | -0.004 |
ths | -0.004 |
Token | incredible |
Token ID | 8082 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ory | +0.035 |
ulu | +0.035 |
J | +0.035 |
common | +0.032 |
ora | +0.031 |
Neg logit contributions | |
oved | -0.035 |
zed | -0.033 |
opes | -0.032 |
ths | -0.031 |
sed | -0.031 |
Token | day |
Token ID | 1110 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ulu | +0.011 |
J | +0.011 |
ory | +0.011 |
common | +0.010 |
Jill | +0.010 |
Neg logit contributions | |
oved | -0.017 |
zed | -0.016 |
opes | -0.016 |
ths | -0.015 |
iously | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
oved | +0.011 |
zed | +0.011 |
opes | +0.011 |
ths | +0.010 |
iously | +0.010 |
Neg logit contributions | |
ulu | -0.007 |
ory | -0.007 |
J | -0.007 |
common | -0.006 |
Jill | -0.006 |
Token | while |
Token ID | 981 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
zed | +0.023 |
oved | +0.023 |
opes | +0.022 |
ths | +0.021 |
iously | +0.021 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.013 |
ory | -0.013 |
ola | -0.012 |
ora | -0.012 |
Token | Benny |
Token ID | 44275 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
oved | +0.009 |
zed | +0.009 |
opes | +0.008 |
ths | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.013 |
J | -0.013 |
ory | -0.013 |
common | -0.012 |
Jill | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
oved | +0.014 |
opes | +0.014 |
zed | +0.014 |
ths | +0.013 |
iously | +0.013 |
Neg logit contributions | |
ulu | -0.010 |
ory | -0.010 |
J | -0.009 |
common | -0.008 |
Jill | -0.008 |
Token | m |
Token ID | 285 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
oved | +0.039 |
opes | +0.038 |
meanings | +0.036 |
ths | +0.036 |
iously | +0.035 |
Neg logit contributions | |
ulu | -0.031 |
ory | -0.028 |
J | -0.027 |
Jill | -0.027 |
mer | -0.026 |
Token | unch |
Token ID | 3316 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
opes | +0.172 |
zed | +0.165 |
meanings | +0.159 |
oved | +0.155 |
sed | +0.153 |
Neg logit contributions | |
ulu | -0.193 |
ory | -0.191 |
J | -0.173 |
ola | -0.164 |
ora | -0.157 |
Token | ing |
Token ID | 278 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
oved | +0.015 |
zed | +0.014 |
opes | +0.013 |
ths | +0.013 |
iously | +0.012 |
Neg logit contributions | |
ulu | -0.022 |
J | -0.022 |
common | -0.021 |
ory | -0.021 |
Jill | -0.021 |
Token | on |
Token ID | 319 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
oved | +0.109 |
zed | +0.105 |
opes | +0.105 |
ths | +0.099 |
iously | +0.098 |
Neg logit contributions | |
ulu | -0.077 |
ory | -0.074 |
J | -0.074 |
common | -0.068 |
Jill | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
oved | +0.079 |
zed | +0.076 |
opes | +0.075 |
ths | +0.072 |
iously | +0.071 |
Neg logit contributions | |
ulu | -0.048 |
ory | -0.046 |
J | -0.046 |
common | -0.042 |
Jill | -0.042 |
Token | carrot |
Token ID | 40562 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ulu | +0.015 |
J | +0.014 |
ory | +0.014 |
Jill | +0.013 |
common | +0.013 |
Neg logit contributions | |
oved | -0.022 |
zed | -0.021 |
opes | -0.021 |
ths | -0.020 |
iously | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ulu | +0.013 |
J | +0.013 |
ory | +0.012 |
Jill | +0.012 |
common | +0.011 |
Neg logit contributions | |
oved | -0.021 |
zed | -0.021 |
opes | -0.020 |
ths | -0.019 |
iously | -0.019 |
Token | did |
Token ID | 750 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
oved | +0.006 |
zed | +0.006 |
opes | +0.006 |
ths | +0.005 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
Jill | -0.005 |
common | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ulu | +0.009 |
J | +0.009 |
common | +0.009 |
Jill | +0.009 |
ory | +0.009 |
Neg logit contributions | |
oved | -0.010 |
opes | -0.010 |
zed | -0.009 |
ths | -0.009 |
iously | -0.009 |
Token | know |
Token ID | 760 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
oved | +0.004 |
ow | +0.004 |
ze | +0.004 |
opes | +0.003 |
zed | +0.003 |
Neg logit contributions | |
ory | -0.006 |
J | -0.006 |
ulu | -0.006 |
ola | -0.005 |
ora | -0.005 |
Token | sun |
Token ID | 4252 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
opes | +0.002 |
erved | +0.002 |
iously | +0.002 |
Neg logit contributions | |
ulu | -0.002 |
Jill | -0.002 |
J | -0.002 |
Jenny | -0.001 |
ory | -0.001 |
Token | fl |
Token ID | 2704 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
zed | +0.084 |
oved | +0.083 |
opes | +0.077 |
iously | +0.075 |
ths | +0.074 |
Neg logit contributions | |
ulu | -0.083 |
J | -0.075 |
ory | -0.074 |
Jill | -0.073 |
common | -0.069 |
Token | owers |
Token ID | 3618 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
zed | +0.158 |
oved | +0.135 |
iously | +0.129 |
opes | +0.127 |
ths | +0.124 |
Neg logit contributions | |
ulu | -0.222 |
ory | -0.204 |
J | -0.196 |
ola | -0.193 |
ora | -0.190 |
Token | could |
Token ID | 714 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
oved | +0.100 |
zed | +0.098 |
opes | +0.096 |
ths | +0.092 |
iously | +0.092 |
Neg logit contributions | |
ulu | -0.067 |
ory | -0.062 |
J | -0.059 |
common | -0.058 |
Jill | -0.057 |
Token | talk |
Token ID | 1561 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
ulu | +0.015 |
J | +0.014 |
ory | +0.014 |
common | +0.013 |
Jill | +0.013 |
Neg logit contributions | |
oved | -0.023 |
zed | -0.022 |
opes | -0.022 |
ths | -0.021 |
iously | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
ulu | +0.010 |
J | +0.010 |
ory | +0.010 |
Jill | +0.009 |
common | +0.009 |
Neg logit contributions | |
oved | -0.017 |
zed | -0.017 |
opes | -0.017 |
ths | -0.017 |
iously | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.003 |
zed | -0.003 |
opes | -0.003 |
iously | -0.003 |
ths | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
oved | +0.006 |
zed | +0.005 |
opes | +0.005 |
sed | +0.005 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.009 |
ory | -0.008 |
J | -0.008 |
common | -0.008 |
ola | -0.008 |
Token | did |
Token ID | 750 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
oved | +0.010 |
zed | +0.010 |
opes | +0.009 |
sed | +0.009 |
ths | +0.009 |
Neg logit contributions | |
ulu | -0.009 |
ory | -0.009 |
J | -0.009 |
common | -0.009 |
ola | -0.008 |
Token | not |
Token ID | 407 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
ory | +0.015 |
ulu | +0.015 |
J | +0.014 |
ora | +0.013 |
ola | +0.013 |
Neg logit contributions | |
zed | -0.008 |
oved | -0.007 |
opes | -0.007 |
ths | -0.006 |
iously | -0.006 |
Token | know |
Token ID | 760 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ow | +0.008 |
oved | +0.008 |
meanings | +0.007 |
about | +0.007 |
ze | +0.007 |
Neg logit contributions | |
ulu | -0.015 |
ola | -0.015 |
ory | -0.014 |
J | -0.014 |
Nina | -0.014 |
Token | sun |
Token ID | 4252 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
oved | +0.010 |
zed | +0.009 |
opes | +0.009 |
ths | +0.009 |
iously | +0.009 |
Neg logit contributions | |
ulu | -0.010 |
J | -0.009 |
ory | -0.009 |
Jill | -0.009 |
common | -0.009 |
Token | fl |
Token ID | 2704 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
oved | +0.082 |
zed | +0.082 |
opes | +0.077 |
ths | +0.073 |
iously | +0.073 |
Neg logit contributions | |
ulu | -0.089 |
J | -0.082 |
ory | -0.082 |
Jill | -0.079 |
common | -0.075 |
Token | owers |
Token ID | 3618 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
zed | +0.148 |
oved | +0.129 |
opes | +0.122 |
erved | +0.118 |
iously | +0.118 |
Neg logit contributions | |
ulu | -0.224 |
ory | -0.211 |
J | -0.200 |
ola | -0.195 |
ora | -0.195 |
Token | were |
Token ID | 547 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
oved | +0.105 |
zed | +0.103 |
opes | +0.102 |
ths | +0.097 |
iously | +0.096 |
Neg logit contributions | |
ulu | -0.070 |
ory | -0.066 |
J | -0.065 |
common | -0.061 |
Jill | -0.060 |
Token | alive |
Token ID | 6776 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
oved | +0.031 |
zed | +0.030 |
opes | +0.030 |
ths | +0.028 |
iously | +0.028 |
Neg logit contributions | |
ulu | -0.026 |
J | -0.025 |
ory | -0.025 |
common | -0.023 |
Jill | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
oved | +0.049 |
zed | +0.049 |
opes | +0.048 |
ths | +0.046 |
iously | +0.045 |
Neg logit contributions | |
ulu | -0.030 |
J | -0.029 |
ory | -0.029 |
Jill | -0.027 |
common | -0.026 |
Token | She |
Token ID | 1375 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
oved | +0.007 |
zed | +0.006 |
opes | +0.006 |
sed | +0.006 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.010 |
ory | -0.010 |
J | -0.009 |
common | -0.009 |
ola | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ulu | +0.004 |
J | +0.004 |
ory | +0.004 |
common | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
oved | -0.004 |
zed | -0.004 |
opes | -0.004 |
ths | -0.004 |
iously | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
zed | +0.023 |
ths | +0.022 |
oved | +0.022 |
opes | +0.022 |
iously | +0.020 |
Neg logit contributions | |
ulu | -0.024 |
ory | -0.023 |
J | -0.022 |
ora | -0.021 |
Col | -0.020 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
oved | +0.033 |
zed | +0.032 |
opes | +0.031 |
ths | +0.030 |
sed | +0.029 |
Neg logit contributions | |
ulu | -0.038 |
ory | -0.037 |
J | -0.037 |
common | -0.035 |
Jill | -0.034 |
Token | â |
Token ID | 22940 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
oved | +0.028 |
zed | +0.027 |
opes | +0.025 |
ths | +0.023 |
iously | +0.023 |
Neg logit contributions | |
ulu | -0.044 |
ory | -0.044 |
J | -0.043 |
common | -0.040 |
Jill | -0.040 |
Token | € |
Token ID | 26391 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
oved | +0.036 |
zed | +0.034 |
opes | +0.032 |
ths | +0.030 |
iously | +0.030 |
Neg logit contributions | |
ulu | -0.044 |
ory | -0.043 |
J | -0.042 |
Jill | -0.040 |
common | -0.040 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
oved | +0.051 |
iously | +0.050 |
zed | +0.048 |
opes | +0.047 |
ths | +0.047 |
Neg logit contributions | |
J | -0.079 |
Jill | -0.071 |
ulu | -0.070 |
ory | -0.069 |
Jenny | -0.067 |
Token | t |
Token ID | 83 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
oved | +0.156 |
zed | +0.145 |
opes | +0.136 |
iously | +0.128 |
ths | +0.126 |
Neg logit contributions | |
ulu | -0.195 |
ory | -0.192 |
J | -0.189 |
common | -0.187 |
Jill | -0.179 |
Token | know |
Token ID | 760 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
ory | +0.002 |
coral | +0.002 |
ulu | +0.002 |
mer | +0.002 |
maid | +0.002 |
Neg logit contributions | |
zed | -0.002 |
about | -0.002 |
oved | -0.002 |
ending | -0.002 |
aged | -0.002 |
Token | which |
Token ID | 543 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
opes | +0.002 |
ths | +0.002 |
iously | +0.002 |
Neg logit contributions | |
ulu | -0.002 |
J | -0.002 |
ory | -0.002 |
Jill | -0.002 |
common | -0.002 |
Token | way |
Token ID | 835 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
ory | +0.007 |
J | +0.007 |
ulu | +0.007 |
ola | +0.006 |
ora | +0.006 |
Neg logit contributions | |
oved | -0.008 |
zed | -0.007 |
opes | -0.007 |
sed | -0.007 |
ths | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
J | +0.020 |
ulu | +0.020 |
ory | +0.020 |
Col | +0.018 |
common | +0.018 |
Neg logit contributions | |
zed | -0.019 |
oved | -0.019 |
opes | -0.018 |
iously | -0.017 |
ths | -0.017 |
Token | restless |
Token ID | 42537 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
opes | +0.040 |
oved | +0.039 |
meanings | +0.037 |
iously | +0.037 |
sed | +0.036 |
Neg logit contributions | |
ulu | -0.031 |
J | -0.028 |
ory | -0.027 |
Jill | -0.027 |
Jenny | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
oved | +0.093 |
opes | +0.093 |
zed | +0.092 |
sed | +0.086 |
ths | +0.086 |
Neg logit contributions | |
ulu | -0.053 |
ory | -0.053 |
J | -0.051 |
Jill | -0.050 |
Jenny | -0.046 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
oved | +0.024 |
zed | +0.023 |
opes | +0.023 |
ths | +0.022 |
iously | +0.022 |
Neg logit contributions | |
ulu | -0.022 |
J | -0.021 |
ory | -0.021 |
common | -0.020 |
Jill | -0.019 |
Token | â |
Token ID | 22940 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
oved | +0.087 |
opes | +0.085 |
sed | +0.080 |
iously | +0.079 |
zed | +0.078 |
Neg logit contributions | |
ulu | -0.086 |
J | -0.082 |
common | -0.078 |
Jill | -0.078 |
ory | -0.077 |
Token | € |
Token ID | 26391 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
oved | +0.034 |
zed | +0.033 |
opes | +0.033 |
ths | +0.030 |
iously | +0.030 |
Neg logit contributions | |
ulu | -0.039 |
J | -0.038 |
ory | -0.038 |
common | -0.035 |
Jill | -0.035 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
iously | +0.080 |
sed | +0.080 |
oved | +0.080 |
meanings | +0.078 |
der | +0.077 |
Neg logit contributions | |
J | -0.099 |
ory | -0.090 |
common | -0.089 |
ulu | -0.087 |
Jenny | -0.085 |
Token | t |
Token ID | 83 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
oved | +0.171 |
zed | +0.164 |
opes | +0.161 |
ths | +0.151 |
iously | +0.150 |
Neg logit contributions | |
ulu | -0.181 |
J | -0.176 |
ory | -0.176 |
common | -0.164 |
Jill | -0.163 |
Token | get |
Token ID | 651 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ulu | +0.008 |
J | +0.008 |
ory | +0.008 |
common | +0.007 |
Jill | +0.007 |
Neg logit contributions | |
oved | -0.010 |
zed | -0.010 |
opes | -0.009 |
iously | -0.009 |
ths | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
J | +0.009 |
ulu | +0.009 |
ory | +0.009 |
common | +0.008 |
ora | +0.008 |
Neg logit contributions | |
zed | -0.009 |
oved | -0.009 |
ths | -0.008 |
iously | -0.008 |
aged | -0.008 |
Token | sleep |
Token ID | 3993 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
zed | +0.032 |
oved | +0.031 |
opes | +0.030 |
iously | +0.029 |
ths | +0.028 |
Neg logit contributions | |
ulu | -0.024 |
J | -0.024 |
ory | -0.024 |
common | -0.021 |
Jill | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
oved | +0.010 |
opes | +0.010 |
zed | +0.009 |
ths | +0.009 |
sed | +0.009 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
common | -0.005 |
Jill | -0.005 |
Token | realised |
Token ID | 19169 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
oved | +0.026 |
opes | +0.025 |
zed | +0.025 |
ths | +0.023 |
iously | +0.023 |
Neg logit contributions | |
ulu | -0.023 |
J | -0.022 |
ory | -0.022 |
Jill | -0.020 |
common | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.022 |
opes | +0.021 |
ths | +0.020 |
iously | +0.019 |
Neg logit contributions | |
ulu | -0.045 |
ory | -0.044 |
J | -0.044 |
common | -0.041 |
Jill | -0.041 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
oved | +0.054 |
opes | +0.053 |
zed | +0.052 |
ths | +0.049 |
iously | +0.049 |
Neg logit contributions | |
ulu | -0.038 |
ory | -0.037 |
J | -0.037 |
Jill | -0.034 |
common | -0.033 |
Token | â |
Token ID | 22940 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
oved | +0.040 |
zed | +0.038 |
opes | +0.038 |
ths | +0.035 |
iously | +0.035 |
Neg logit contributions | |
ulu | -0.052 |
J | -0.050 |
ory | -0.050 |
common | -0.047 |
Jill | -0.047 |
Token | € |
Token ID | 26391 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
oved | +0.051 |
zed | +0.049 |
opes | +0.045 |
iously | +0.044 |
ths | +0.043 |
Neg logit contributions | |
ulu | -0.044 |
J | -0.042 |
ory | -0.042 |
Jill | -0.039 |
common | -0.039 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
opes | +0.076 |
oved | +0.076 |
iously | +0.075 |
meanings | +0.070 |
zed | +0.070 |
Neg logit contributions | |
J | -0.102 |
ory | -0.090 |
Jill | -0.090 |
ulu | -0.089 |
Jenny | -0.085 |
Token | t |
Token ID | 83 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
oved | +0.173 |
opes | +0.168 |
zed | +0.167 |
ths | +0.156 |
iously | +0.154 |
Neg logit contributions | |
ulu | -0.178 |
J | -0.172 |
ory | -0.172 |
Jill | -0.158 |
common | -0.157 |
Token | scared |
Token ID | 12008 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
oved | +0.001 |
zed | +0.001 |
opes | +0.001 |
ths | +0.001 |
iously | +0.001 |
Neg logit contributions | |
ulu | -0.001 |
J | -0.001 |
ory | -0.001 |
common | -0.001 |
Jill | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
oved | +0.048 |
zed | +0.046 |
opes | +0.046 |
ths | +0.042 |
iously | +0.042 |
Neg logit contributions | |
ulu | -0.055 |
ory | -0.053 |
J | -0.053 |
Jill | -0.050 |
common | -0.049 |
Token | go |
Token ID | 467 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
oved | +0.015 |
zed | +0.014 |
opes | +0.014 |
iously | +0.013 |
ths | +0.013 |
Neg logit contributions | |
ulu | -0.012 |
J | -0.012 |
ory | -0.011 |
common | -0.010 |
Jill | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
J | +0.003 |
ory | +0.003 |
ulu | +0.003 |
common | +0.003 |
Col | +0.003 |
Neg logit contributions | |
oved | -0.002 |
zed | -0.002 |
ths | -0.002 |
iously | -0.002 |
erved | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
oved | +0.052 |
zed | +0.051 |
opes | +0.050 |
ths | +0.048 |
iously | +0.047 |
Neg logit contributions | |
ulu | -0.040 |
J | -0.039 |
ory | -0.039 |
common | -0.035 |
Jill | -0.035 |
Token | Mike |
Token ID | 4995 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
oved | +0.039 |
zed | +0.038 |
ths | +0.035 |
opes | +0.035 |
iously | +0.034 |
Neg logit contributions | |
ulu | -0.035 |
J | -0.034 |
ory | -0.033 |
common | -0.031 |
ora | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ulu | +0.024 |
ory | +0.023 |
J | +0.023 |
Jill | +0.021 |
common | +0.020 |
Neg logit contributions | |
oved | -0.032 |
opes | -0.031 |
zed | -0.031 |
ths | -0.030 |
sed | -0.030 |
Token | his |
Token ID | 465 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
zed | +0.069 |
oved | +0.064 |
aged | +0.060 |
iously | +0.059 |
ths | +0.058 |
Neg logit contributions | |
ory | -0.053 |
ulu | -0.050 |
J | -0.048 |
common | -0.043 |
ackers | -0.043 |
Token | m |
Token ID | 285 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
oved | +0.093 |
zed | +0.092 |
opes | +0.090 |
iously | +0.085 |
ths | +0.084 |
Neg logit contributions | |
ulu | -0.059 |
ory | -0.055 |
J | -0.055 |
Jill | -0.049 |
common | -0.049 |
Token | itten |
Token ID | 2621 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
zed | +0.124 |
opes | +0.114 |
oved | +0.114 |
storms | +0.105 |
sed | +0.105 |
Neg logit contributions | |
ulu | -0.173 |
ory | -0.160 |
J | -0.157 |
ola | -0.148 |
ora | -0.140 |
Token | were |
Token ID | 547 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
oved | +0.203 |
opes | +0.197 |
iously | +0.189 |
zed | +0.188 |
ths | +0.183 |
Neg logit contributions | |
ulu | -0.137 |
ory | -0.119 |
J | -0.113 |
water | -0.110 |
Jill | -0.110 |
Token | insepar |
Token ID | 50140 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
oved | +0.048 |
opes | +0.046 |
zed | +0.046 |
iously | +0.044 |
sed | +0.043 |
Neg logit contributions | |
ulu | -0.047 |
J | -0.045 |
ory | -0.044 |
Jill | -0.042 |
common | -0.042 |
Token | able |
Token ID | 540 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
oved | +0.098 |
zed | +0.092 |
ths | +0.086 |
chair | +0.085 |
ending | +0.084 |
Neg logit contributions | |
ulu | -0.065 |
J | -0.060 |
common | -0.056 |
ory | -0.056 |
Jill | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
zed | +0.082 |
oved | +0.080 |
opes | +0.078 |
ths | +0.075 |
erved | +0.074 |
Neg logit contributions | |
ory | -0.039 |
ulu | -0.038 |
J | -0.035 |
Jill | -0.034 |
Jenny | -0.031 |
Token | They |
Token ID | 1119 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
oved | +0.033 |
zed | +0.032 |
opes | +0.031 |
iously | +0.029 |
ths | +0.029 |
Neg logit contributions | |
ulu | -0.030 |
ory | -0.029 |
J | -0.029 |
common | -0.026 |
Jill | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
oved | +0.045 |
zed | +0.044 |
opes | +0.042 |
ths | +0.041 |
iously | +0.040 |
Neg logit contributions | |
ulu | -0.037 |
J | -0.036 |
ory | -0.035 |
common | -0.033 |
Jill | -0.032 |
Token | Molly |
Token ID | 30236 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
zed | +0.038 |
oved | +0.037 |
ths | +0.035 |
iously | +0.034 |
opes | +0.033 |
Neg logit contributions | |
J | -0.020 |
ulu | -0.020 |
ory | -0.019 |
common | -0.019 |
Ar | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
oved | +0.031 |
opes | +0.031 |
zed | +0.029 |
iously | +0.029 |
sed | +0.029 |
Neg logit contributions | |
ory | -0.024 |
ulu | -0.024 |
J | -0.023 |
Jill | -0.022 |
common | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
oved | +0.076 |
zed | +0.075 |
opes | +0.073 |
ths | +0.070 |
iously | +0.069 |
Neg logit contributions | |
ulu | -0.051 |
J | -0.049 |
ory | -0.049 |
common | -0.044 |
Jill | -0.043 |
Token | m |
Token ID | 285 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
oved | +0.107 |
zed | +0.104 |
opes | +0.102 |
iously | +0.097 |
ths | +0.097 |
Neg logit contributions | |
ulu | -0.056 |
J | -0.054 |
ory | -0.054 |
Jill | -0.049 |
common | -0.047 |
Token | ule |
Token ID | 2261 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
zed | +0.139 |
oved | +0.131 |
opes | +0.125 |
sed | +0.122 |
ths | +0.116 |
Neg logit contributions | |
ulu | -0.184 |
ory | -0.184 |
J | -0.174 |
ola | -0.161 |
ora | -0.157 |
Token | were |
Token ID | 547 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
oved | +0.189 |
iously | +0.184 |
opes | +0.182 |
zed | +0.178 |
sed | +0.174 |
Neg logit contributions | |
ulu | -0.145 |
ory | -0.138 |
J | -0.137 |
Jill | -0.131 |
ola | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
oved | +0.078 |
opes | +0.077 |
sed | +0.076 |
iously | +0.074 |
zed | +0.072 |
Neg logit contributions | |
ulu | -0.054 |
J | -0.052 |
Jill | -0.049 |
ory | -0.049 |
common | -0.046 |
Token | best |
Token ID | 1266 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
oved | +0.050 |
zed | +0.047 |
opes | +0.046 |
ths | +0.044 |
iously | +0.043 |
Neg logit contributions | |
ulu | -0.071 |
J | -0.069 |
ory | -0.069 |
Jill | -0.065 |
common | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
opes | +0.036 |
oved | +0.036 |
zed | +0.036 |
sed | +0.034 |
iously | +0.034 |
Neg logit contributions | |
ulu | -0.022 |
ory | -0.021 |
J | -0.020 |
Jill | -0.019 |
ola | -0.018 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
oved | +0.064 |
zed | +0.062 |
opes | +0.061 |
iously | +0.058 |
ths | +0.057 |
Neg logit contributions | |
ulu | -0.045 |
J | -0.042 |
ory | -0.042 |
Jill | -0.039 |
common | -0.039 |
Token | They |
Token ID | 1119 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ulu | +0.002 |
J | +0.002 |
ory | +0.002 |
common | +0.002 |
ola | +0.002 |
Neg logit contributions | |
oved | -0.005 |
zed | -0.004 |
opes | -0.004 |
sed | -0.004 |
iously | -0.004 |
Token | want |
Token ID | 765 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
oved | +0.028 |
opes | +0.027 |
zed | +0.027 |
sed | +0.024 |
ths | +0.024 |
Neg logit contributions | |
ulu | -0.023 |
ory | -0.023 |
J | -0.022 |
common | -0.021 |
Jill | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ulu | +0.008 |
ory | +0.007 |
J | +0.007 |
common | +0.007 |
ola | +0.007 |
Neg logit contributions | |
oved | -0.004 |
opes | -0.004 |
zed | -0.004 |
ths | -0.004 |
iously | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
oved | +0.006 |
zed | +0.006 |
opes | +0.006 |
ze | +0.006 |
ths | +0.006 |
Neg logit contributions | |
ory | -0.005 |
ulu | -0.005 |
J | -0.005 |
ora | -0.004 |
ola | -0.004 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
oved | +0.031 |
opes | +0.031 |
zed | +0.030 |
ths | +0.029 |
iously | +0.028 |
Neg logit contributions | |
ulu | -0.028 |
ory | -0.027 |
J | -0.026 |
common | -0.024 |
ola | -0.023 |
Token | fl |
Token ID | 2704 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
oved | +0.054 |
zed | +0.052 |
opes | +0.052 |
ths | +0.049 |
iously | +0.048 |
Neg logit contributions | |
ulu | -0.050 |
J | -0.049 |
ory | -0.048 |
Jill | -0.045 |
common | -0.045 |
Token | akes |
Token ID | 1124 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
zed | +0.158 |
iously | +0.145 |
oved | +0.142 |
sed | +0.142 |
opes | +0.134 |
Neg logit contributions | |
ulu | -0.192 |
J | -0.178 |
ory | -0.173 |
ola | -0.173 |
Jill | -0.167 |
Token | for |
Token ID | 329 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
oved | +0.078 |
zed | +0.076 |
opes | +0.074 |
ths | +0.070 |
iously | +0.069 |
Neg logit contributions | |
J | -0.069 |
ory | -0.069 |
ulu | -0.068 |
common | -0.062 |
Jill | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
oved | +0.060 |
zed | +0.058 |
opes | +0.058 |
ths | +0.055 |
iously | +0.054 |
Neg logit contributions | |
ulu | -0.047 |
ory | -0.045 |
J | -0.045 |
common | -0.041 |
Jill | -0.041 |
Token | window |
Token ID | 4324 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
oved | +0.010 |
opes | +0.010 |
zed | +0.010 |
ths | +0.009 |
iously | +0.009 |
Neg logit contributions | |
ulu | -0.008 |
J | -0.008 |
ory | -0.008 |
common | -0.007 |
Jill | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.022 |
opes | +0.022 |
ths | +0.020 |
iously | +0.020 |
Neg logit contributions | |
ulu | -0.016 |
J | -0.015 |
ory | -0.015 |
common | -0.014 |
Jill | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
oved | +0.065 |
opes | +0.064 |
zed | +0.062 |
iously | +0.060 |
sed | +0.059 |
Neg logit contributions | |
ulu | -0.047 |
J | -0.044 |
ory | -0.043 |
Jill | -0.042 |
common | -0.039 |
Token | their |
Token ID | 511 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
oved | +0.056 |
opes | +0.054 |
zed | +0.053 |
iously | +0.051 |
sed | +0.050 |
Neg logit contributions | |
ulu | -0.045 |
J | -0.043 |
ory | -0.042 |
Jill | -0.040 |
common | -0.040 |
Token | son |
Token ID | 3367 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
oved | +0.088 |
zed | +0.087 |
opes | +0.087 |
iously | +0.079 |
ths | +0.079 |
Neg logit contributions | |
ulu | -0.072 |
ory | -0.071 |
J | -0.070 |
common | -0.067 |
Jill | -0.066 |
Token | â |
Token ID | 22940 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
oved | +0.092 |
opes | +0.091 |
zed | +0.090 |
ths | +0.084 |
iously | +0.084 |
Neg logit contributions | |
ulu | -0.065 |
ory | -0.063 |
J | -0.062 |
Jill | -0.058 |
common | -0.057 |
Token | € |
Token ID | 26391 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
oved | +0.027 |
zed | +0.026 |
opes | +0.025 |
ths | +0.024 |
iously | +0.024 |
Neg logit contributions | |
ulu | -0.032 |
J | -0.031 |
ory | -0.031 |
Jill | -0.029 |
common | -0.029 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
iously | +0.093 |
oved | +0.090 |
opes | +0.087 |
sed | +0.086 |
der | +0.085 |
Neg logit contributions | |
J | -0.066 |
Jill | -0.056 |
ory | -0.054 |
ulu | -0.053 |
Jenny | -0.052 |
Token | s |
Token ID | 82 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
oved | +0.195 |
opes | +0.191 |
zed | +0.189 |
ths | +0.180 |
iously | +0.179 |
Neg logit contributions | |
ulu | -0.150 |
J | -0.145 |
ory | -0.144 |
Jill | -0.131 |
common | -0.128 |
Token | special |
Token ID | 2041 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
opes | +0.062 |
zed | +0.061 |
oved | +0.061 |
ths | +0.057 |
iously | +0.057 |
Neg logit contributions | |
ulu | -0.038 |
Jill | -0.036 |
J | -0.036 |
ory | -0.036 |
common | -0.035 |
Token | place |
Token ID | 1295 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
oved | +0.013 |
zed | +0.013 |
opes | +0.013 |
iously | +0.012 |
ths | +0.012 |
Neg logit contributions | |
ulu | -0.008 |
J | -0.008 |
ory | -0.008 |
Jill | -0.008 |
common | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
ulu | +0.019 |
J | +0.019 |
ory | +0.019 |
common | +0.017 |
Jill | +0.017 |
Neg logit contributions | |
oved | -0.022 |
zed | -0.021 |
opes | -0.021 |
ths | -0.019 |
iously | -0.019 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.023 |
opes | +0.022 |
ths | +0.021 |
iously | +0.020 |
Neg logit contributions | |
ulu | -0.018 |
J | -0.017 |
ory | -0.017 |
common | -0.016 |
ora | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
oved | +0.037 |
opes | +0.035 |
sed | +0.033 |
iously | +0.033 |
ths | +0.033 |
Neg logit contributions | |
ulu | -0.031 |
J | -0.029 |
ory | -0.029 |
Jill | -0.028 |
common | -0.028 |
Token | send |
Token ID | 3758 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
oved | +0.070 |
zed | +0.069 |
opes | +0.067 |
ths | +0.064 |
iously | +0.063 |
Neg logit contributions | |
ulu | -0.051 |
J | -0.049 |
ory | -0.049 |
Jill | -0.045 |
common | -0.044 |
Token | soft |
Token ID | 2705 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
ulu | +0.019 |
ory | +0.018 |
J | +0.018 |
ola | +0.016 |
common | +0.016 |
Neg logit contributions | |
oved | -0.021 |
zed | -0.020 |
opes | -0.020 |
iously | -0.019 |
ths | -0.019 |
Token | white |
Token ID | 2330 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
oved | +0.029 |
zed | +0.028 |
opes | +0.028 |
iously | +0.026 |
ths | +0.026 |
Neg logit contributions | |
ulu | -0.028 |
J | -0.027 |
ory | -0.027 |
Jill | -0.025 |
common | -0.025 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
oved | +0.037 |
zed | +0.035 |
opes | +0.035 |
ths | +0.033 |
iously | +0.033 |
Neg logit contributions | |
ulu | -0.034 |
J | -0.033 |
ory | -0.033 |
common | -0.031 |
Jill | -0.030 |
Token | fl |
Token ID | 2704 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
oved | +0.057 |
zed | +0.055 |
opes | +0.054 |
ths | +0.051 |
iously | +0.050 |
Neg logit contributions | |
ulu | -0.058 |
ory | -0.056 |
J | -0.055 |
Jill | -0.052 |
common | -0.051 |
Token | akes |
Token ID | 1124 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
zed | +0.137 |
oved | +0.121 |
sed | +0.116 |
opes | +0.114 |
iously | +0.110 |
Neg logit contributions | |
ulu | -0.206 |
ory | -0.201 |
J | -0.188 |
ola | -0.183 |
Jill | -0.182 |
Token | into |
Token ID | 656 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
oved | +0.082 |
zed | +0.079 |
opes | +0.077 |
iously | +0.073 |
ths | +0.073 |
Neg logit contributions | |
ulu | -0.078 |
J | -0.077 |
ory | -0.076 |
common | -0.070 |
Jill | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
oved | +0.069 |
zed | +0.068 |
opes | +0.067 |
ths | +0.063 |
iously | +0.062 |
Neg logit contributions | |
ory | -0.052 |
ulu | -0.050 |
J | -0.049 |
common | -0.043 |
ora | -0.043 |
Token | sky |
Token ID | 6766 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
oved | +0.016 |
zed | +0.015 |
opes | +0.015 |
ths | +0.014 |
iously | +0.014 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.013 |
ory | -0.013 |
common | -0.012 |
Jill | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ulu | +0.040 |
J | +0.039 |
ory | +0.039 |
Jill | +0.035 |
common | +0.035 |
Neg logit contributions | |
oved | -0.062 |
zed | -0.060 |
opes | -0.060 |
ths | -0.057 |
iously | -0.056 |
Token | bear |
Token ID | 6842 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
ulu | +0.002 |
J | +0.002 |
ory | +0.002 |
Jill | +0.002 |
common | +0.002 |
Neg logit contributions | |
oved | -0.003 |
opes | -0.003 |
zed | -0.003 |
ths | -0.002 |
iously | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
oved | +0.025 |
zed | +0.024 |
opes | +0.024 |
ths | +0.024 |
sed | +0.023 |
Neg logit contributions | |
ulu | -0.015 |
ory | -0.014 |
J | -0.013 |
Jill | -0.013 |
common | -0.012 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ulu | +0.007 |
ory | +0.006 |
J | +0.006 |
Jill | +0.006 |
common | +0.006 |
Neg logit contributions | |
oved | -0.007 |
opes | -0.006 |
zed | -0.006 |
ths | -0.006 |
iously | -0.006 |
Token | â |
Token ID | 22940 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
oved | +0.042 |
opes | +0.041 |
zed | +0.040 |
iously | +0.038 |
ths | +0.038 |
Neg logit contributions | |
ulu | -0.047 |
J | -0.045 |
ory | -0.043 |
common | -0.042 |
Jill | -0.041 |
Token | € |
Token ID | 26391 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
oved | +0.026 |
zed | +0.025 |
opes | +0.024 |
iously | +0.022 |
ths | +0.022 |
Neg logit contributions | |
ulu | -0.032 |
ory | -0.031 |
J | -0.031 |
Jill | -0.029 |
common | -0.029 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
iously | +0.048 |
oved | +0.048 |
ths | +0.046 |
der | +0.044 |
zed | +0.044 |
Neg logit contributions | |
J | -0.062 |
ulu | -0.055 |
Jill | -0.053 |
ory | -0.053 |
common | -0.053 |
Token | t |
Token ID | 83 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
oved | +0.160 |
zed | +0.152 |
opes | +0.148 |
iously | +0.137 |
ths | +0.137 |
Neg logit contributions | |
ulu | -0.182 |
ory | -0.179 |
J | -0.178 |
common | -0.170 |
Jill | -0.165 |
Token | want |
Token ID | 765 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
oved | +0.015 |
zed | +0.014 |
opes | +0.014 |
erved | +0.013 |
ending | +0.012 |
Neg logit contributions | |
ory | -0.013 |
ulu | -0.012 |
J | -0.012 |
ola | -0.011 |
Jill | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
ulu | +0.019 |
J | +0.019 |
ory | +0.019 |
Jill | +0.018 |
common | +0.018 |
Neg logit contributions | |
oved | -0.018 |
opes | -0.017 |
zed | -0.017 |
ths | -0.016 |
iously | -0.016 |
Token | go |
Token ID | 467 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
oved | +0.022 |
zed | +0.022 |
opes | +0.021 |
iously | +0.020 |
ths | +0.020 |
Neg logit contributions | |
ulu | -0.018 |
J | -0.018 |
ory | -0.018 |
Jill | -0.016 |
ola | -0.016 |
Token | anywhere |
Token ID | 6609 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
erved | +0.002 |
opes | +0.002 |
iously | +0.002 |
Neg logit contributions | |
J | -0.004 |
ory | -0.004 |
ulu | -0.004 |
ola | -0.003 |
Col | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
ulu | +0.021 |
J | +0.020 |
ory | +0.020 |
common | +0.018 |
ola | +0.018 |
Neg logit contributions | |
oved | -0.027 |
zed | -0.026 |
opes | -0.026 |
ths | -0.024 |
iously | -0.024 |
Token | played |
Token ID | 2826 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
oved | +0.032 |
zed | +0.031 |
opes | +0.031 |
iously | +0.029 |
ths | +0.029 |
Neg logit contributions | |
ulu | -0.029 |
ory | -0.028 |
J | -0.028 |
Jill | -0.026 |
common | -0.026 |
Token | make |
Token ID | 787 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
ulu | +0.019 |
ory | +0.018 |
J | +0.018 |
common | +0.016 |
Jill | +0.016 |
Neg logit contributions | |
oved | -0.024 |
zed | -0.024 |
opes | -0.023 |
ths | -0.022 |
iously | -0.022 |
Token | - |
Token ID | 12 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
oved | +0.025 |
zed | +0.025 |
opes | +0.024 |
ths | +0.022 |
iously | +0.022 |
Neg logit contributions | |
ulu | -0.025 |
ory | -0.024 |
J | -0.023 |
common | -0.022 |
ora | -0.021 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
oved | +0.050 |
zed | +0.047 |
opes | +0.045 |
ths | +0.041 |
iously | +0.040 |
Neg logit contributions | |
ulu | -0.096 |
ory | -0.095 |
J | -0.093 |
common | -0.090 |
Jill | -0.089 |
Token | ieve |
Token ID | 12311 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
sed | +0.175 |
iously | +0.159 |
opes | +0.158 |
oved | +0.158 |
zed | +0.148 |
Neg logit contributions | |
J | -0.178 |
ulu | -0.162 |
common | -0.159 |
ola | -0.154 |
Jill | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
ulu | +0.033 |
ory | +0.032 |
J | +0.031 |
common | +0.028 |
Jill | +0.028 |
Neg logit contributions | |
oved | -0.044 |
zed | -0.042 |
opes | -0.041 |
ths | -0.039 |
iously | -0.039 |
Token | Finally |
Token ID | 9461 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
oved | +0.033 |
zed | +0.033 |
opes | +0.032 |
iously | +0.030 |
ths | +0.030 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.013 |
ory | -0.013 |
common | -0.012 |
Jill | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
zed | +0.016 |
oved | +0.014 |
ths | +0.013 |
iously | +0.012 |
opes | +0.012 |
Neg logit contributions | |
ulu | -0.021 |
ory | -0.020 |
J | -0.019 |
common | -0.019 |
rust | -0.018 |
Token | they |
Token ID | 484 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
zed | +0.050 |
oved | +0.046 |
ths | +0.043 |
opes | +0.042 |
erved | +0.042 |
Neg logit contributions | |
ulu | -0.043 |
J | -0.037 |
ory | -0.036 |
common | -0.036 |
ola | -0.034 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
oved | +0.021 |
zed | +0.020 |
opes | +0.020 |
iously | +0.020 |
ths | +0.019 |
Neg logit contributions | |
ulu | -0.017 |
J | -0.016 |
Jill | -0.016 |
ory | -0.015 |
Jenny | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
zed | +0.052 |
oved | +0.052 |
opes | +0.050 |
sed | +0.047 |
ths | +0.047 |
Neg logit contributions | |
ory | -0.038 |
Jill | -0.038 |
J | -0.037 |
ulu | -0.037 |
Jenny | -0.035 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
oved | +0.003 |
zed | +0.003 |
opes | +0.003 |
ths | +0.002 |
iously | +0.002 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
Jill | -0.003 |
common | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
oved | +0.065 |
opes | +0.063 |
zed | +0.061 |
iously | +0.059 |
ths | +0.058 |
Neg logit contributions | |
ulu | -0.079 |
J | -0.076 |
ory | -0.074 |
Jill | -0.072 |
common | -0.071 |
Token | € |
Token ID | 26391 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
oved | +0.029 |
zed | +0.028 |
opes | +0.026 |
ths | +0.025 |
iously | +0.025 |
Neg logit contributions | |
ulu | -0.033 |
ory | -0.031 |
J | -0.031 |
Jill | -0.029 |
common | -0.029 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
oved | +0.073 |
iously | +0.072 |
opes | +0.070 |
ths | +0.069 |
zed | +0.068 |
Neg logit contributions | |
J | -0.078 |
ulu | -0.071 |
Jill | -0.071 |
ory | -0.070 |
common | -0.070 |
Token | t |
Token ID | 83 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
oved | +0.153 |
zed | +0.141 |
opes | +0.134 |
iously | +0.127 |
ths | +0.125 |
Neg logit contributions | |
ulu | -0.188 |
ory | -0.184 |
J | -0.183 |
common | -0.179 |
Jill | -0.172 |
Token | wait |
Token ID | 4043 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ulu | +0.019 |
ory | +0.018 |
J | +0.018 |
common | +0.017 |
ora | +0.016 |
Neg logit contributions | |
oved | -0.018 |
zed | -0.018 |
iously | -0.016 |
opes | -0.016 |
ths | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ulu | +0.043 |
J | +0.043 |
Jill | +0.041 |
ory | +0.041 |
common | +0.040 |
Neg logit contributions | |
oved | -0.056 |
opes | -0.053 |
zed | -0.051 |
ths | -0.050 |
sed | -0.049 |
Token | have |
Token ID | 423 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
zed | +0.020 |
oved | +0.019 |
opes | +0.019 |
ths | +0.018 |
erved | +0.018 |
Neg logit contributions | |
ulu | -0.020 |
ory | -0.019 |
J | -0.019 |
ora | -0.016 |
ola | -0.016 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ulu | +0.025 |
ory | +0.024 |
J | +0.023 |
ora | +0.022 |
ola | +0.021 |
Neg logit contributions | |
zed | -0.026 |
oved | -0.026 |
opes | -0.025 |
ths | -0.024 |
erved | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
oved | +0.121 |
zed | +0.119 |
opes | +0.119 |
ths | +0.114 |
sed | +0.110 |
Neg logit contributions | |
ulu | -0.083 |
ory | -0.081 |
J | -0.079 |
Jill | -0.074 |
common | -0.070 |
Token | Jake |
Token ID | 14757 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
ulu | +0.010 |
J | +0.010 |
ory | +0.010 |
Jill | +0.009 |
common | +0.009 |
Neg logit contributions | |
oved | -0.013 |
zed | -0.013 |
opes | -0.012 |
ths | -0.012 |
iously | -0.012 |
Token | had |
Token ID | 550 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ory | +0.021 |
ulu | +0.020 |
J | +0.020 |
Jill | +0.019 |
Jenny | +0.018 |
Neg logit contributions | |
oved | -0.031 |
opes | -0.030 |
zed | -0.029 |
ths | -0.028 |
iously | -0.027 |
Token | never |
Token ID | 1239 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
J | +0.016 |
ulu | +0.016 |
ory | +0.015 |
Jill | +0.015 |
common | +0.014 |
Neg logit contributions | |
oved | -0.019 |
opes | -0.018 |
zed | -0.017 |
ths | -0.017 |
iously | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ulu | +0.004 |
J | +0.004 |
ory | +0.004 |
Jill | +0.003 |
common | +0.003 |
Neg logit contributions | |
oved | -0.004 |
opes | -0.004 |
zed | -0.004 |
ths | -0.004 |
iously | -0.004 |
Token | por |
Token ID | 16964 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
ulu | +0.011 |
J | +0.010 |
ory | +0.010 |
Jill | +0.010 |
common | +0.009 |
Neg logit contributions | |
oved | -0.013 |
opes | -0.012 |
zed | -0.012 |
ths | -0.012 |
iously | -0.012 |
Token | ridge |
Token ID | 12818 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
oved | +0.113 |
ths | +0.103 |
opes | +0.097 |
zed | +0.095 |
sed | +0.094 |
Neg logit contributions | |
ory | -0.213 |
J | -0.206 |
ulu | -0.204 |
opener | -0.194 |
Jolly | -0.193 |
Token | before |
Token ID | 878 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
oved | +0.190 |
opes | +0.188 |
zed | +0.184 |
ths | +0.176 |
sed | +0.173 |
Neg logit contributions | |
ulu | -0.114 |
ory | -0.112 |
J | -0.111 |
Jill | -0.101 |
common | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
oved | +0.018 |
zed | +0.017 |
opes | +0.017 |
ths | +0.016 |
sed | +0.016 |
Neg logit contributions | |
ulu | -0.011 |
ory | -0.010 |
J | -0.010 |
Jill | -0.010 |
common | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
ulu | +0.018 |
J | +0.017 |
ory | +0.017 |
Jill | +0.016 |
common | +0.015 |
Neg logit contributions | |
oved | -0.031 |
zed | -0.030 |
opes | -0.030 |
ths | -0.028 |
iously | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
oved | +0.024 |
opes | +0.024 |
zed | +0.023 |
ths | +0.022 |
iously | +0.022 |
Neg logit contributions | |
ulu | -0.017 |
ory | -0.017 |
J | -0.017 |
Jill | -0.016 |
common | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
oved | +0.007 |
zed | +0.007 |
opes | +0.007 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
common | -0.006 |
ory | -0.006 |
Jill | -0.005 |
Token | Jack |
Token ID | 3619 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
iously | +0.018 |
ths | +0.018 |
sed | +0.017 |
zed | +0.017 |
oved | +0.017 |
Neg logit contributions | |
ulu | -0.021 |
common | -0.020 |
Ar | -0.019 |
opener | -0.019 |
J | -0.019 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
oved | +0.021 |
zed | +0.021 |
opes | +0.021 |
ths | +0.019 |
iously | +0.019 |
Neg logit contributions | |
ulu | -0.016 |
ory | -0.015 |
J | -0.015 |
Jill | -0.014 |
ola | -0.013 |
Token | â |
Token ID | 22940 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
oved | +0.035 |
opes | +0.033 |
zed | +0.032 |
sed | +0.031 |
iously | +0.030 |
Neg logit contributions | |
ulu | -0.040 |
J | -0.039 |
ory | -0.038 |
common | -0.036 |
Jill | -0.036 |
Token | € |
Token ID | 26391 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
oved | +0.039 |
zed | +0.037 |
opes | +0.036 |
ths | +0.034 |
iously | +0.034 |
Neg logit contributions | |
ulu | -0.042 |
J | -0.041 |
ory | -0.041 |
common | -0.038 |
Jill | -0.038 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
oved | +0.066 |
opes | +0.063 |
zed | +0.061 |
iously | +0.061 |
ths | +0.059 |
Neg logit contributions | |
J | -0.090 |
ory | -0.086 |
ulu | -0.084 |
Jill | -0.083 |
Jenny | -0.079 |
Token | t |
Token ID | 83 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
oved | +0.160 |
zed | +0.152 |
opes | +0.147 |
iously | +0.138 |
ths | +0.137 |
Neg logit contributions | |
ulu | -0.179 |
J | -0.175 |
ory | -0.175 |
common | -0.166 |
Jill | -0.163 |
Token | give |
Token ID | 1577 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
opes | +0.002 |
ze | +0.002 |
ending | +0.002 |
Neg logit contributions | |
J | -0.002 |
ulu | -0.002 |
ory | -0.002 |
common | -0.002 |
ora | -0.002 |
Token | up |
Token ID | 510 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ulu | +0.084 |
J | +0.084 |
Ar | +0.078 |
opener | +0.078 |
ory | +0.076 |
Neg logit contributions | |
zed | -0.060 |
oved | -0.057 |
opes | -0.055 |
ths | -0.055 |
iously | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
oved | +0.037 |
zed | +0.036 |
opes | +0.035 |
iously | +0.034 |
ths | +0.034 |
Neg logit contributions | |
ulu | -0.032 |
J | -0.030 |
ory | -0.030 |
common | -0.027 |
Jill | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
oved | +0.003 |
zed | +0.003 |
opes | +0.003 |
iously | +0.002 |
ths | +0.002 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
common | -0.003 |
ora | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ulu | +0.040 |
J | +0.038 |
ory | +0.037 |
Jill | +0.034 |
common | +0.034 |
Neg logit contributions | |
oved | -0.052 |
zed | -0.049 |
opes | -0.048 |
iously | -0.046 |
ths | -0.045 |
Token | They |
Token ID | 1119 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.008 |
opes | +0.008 |
sed | +0.007 |
ths | +0.007 |
Neg logit contributions | |
ulu | -0.007 |
ory | -0.007 |
J | -0.007 |
ola | -0.006 |
Jill | -0.006 |
Token | never |
Token ID | 1239 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.022 |
opes | +0.022 |
ths | +0.020 |
iously | +0.020 |
Neg logit contributions | |
ulu | -0.030 |
J | -0.029 |
ory | -0.029 |
common | -0.027 |
Jill | -0.027 |
Token | planted |
Token ID | 18969 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
oved | +0.037 |
zed | +0.036 |
opes | +0.035 |
ths | +0.033 |
iously | +0.033 |
Neg logit contributions | |
ulu | -0.031 |
J | -0.030 |
ory | -0.030 |
common | -0.027 |
Jill | -0.027 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
oved | +0.017 |
zed | +0.016 |
opes | +0.016 |
ths | +0.015 |
iously | +0.015 |
Neg logit contributions | |
ulu | -0.013 |
J | -0.013 |
ory | -0.013 |
ola | -0.011 |
Jill | -0.011 |
Token | fl |
Token ID | 2704 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
oved | +0.058 |
zed | +0.056 |
opes | +0.055 |
ths | +0.052 |
iously | +0.052 |
Neg logit contributions | |
ulu | -0.037 |
J | -0.035 |
ory | -0.035 |
Jill | -0.032 |
common | -0.032 |
Token | owers |
Token ID | 3618 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
zed | +0.136 |
oved | +0.119 |
opes | +0.116 |
sed | +0.110 |
iously | +0.109 |
Neg logit contributions | |
ulu | -0.213 |
ory | -0.206 |
J | -0.195 |
ola | -0.188 |
ora | -0.187 |
Token | again |
Token ID | 757 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
oved | +0.077 |
zed | +0.073 |
opes | +0.072 |
ths | +0.068 |
iously | +0.068 |
Neg logit contributions | |
ulu | -0.064 |
J | -0.064 |
ory | -0.062 |
common | -0.058 |
Jill | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ulu | +0.002 |
ory | +0.002 |
J | +0.002 |
Jill | +0.002 |
common | +0.002 |
Neg logit contributions | |
oved | -0.003 |
zed | -0.002 |
opes | -0.002 |
iously | -0.002 |
ths | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
oved | +0.021 |
zed | +0.020 |
opes | +0.020 |
sed | +0.019 |
ths | +0.018 |
Neg logit contributions | |
ulu | -0.017 |
ory | -0.016 |
J | -0.016 |
ola | -0.014 |
Jill | -0.014 |
Token | L |
Token ID | 43 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ory | +0.003 |
ulu | +0.002 |
J | +0.002 |
common | +0.002 |
Jill | +0.002 |
Neg logit contributions | |
oved | -0.002 |
zed | -0.002 |
opes | -0.002 |
ow | -0.002 |
Leave | -0.002 |
Token | onwards |
Token ID | 31719 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
opes | +0.072 |
oved | +0.072 |
iously | +0.067 |
sed | +0.067 |
zed | +0.066 |
Neg logit contributions | |
ulu | -0.050 |
J | -0.049 |
ory | -0.046 |
Jill | -0.043 |
ola | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
oved | +0.045 |
zed | +0.044 |
opes | +0.042 |
ths | +0.041 |
iously | +0.040 |
Neg logit contributions | |
ulu | -0.037 |
J | -0.036 |
ory | -0.035 |
common | -0.033 |
Jill | -0.032 |
Token | Molly |
Token ID | 30236 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
zed | +0.038 |
oved | +0.037 |
ths | +0.035 |
iously | +0.034 |
opes | +0.033 |
Neg logit contributions | |
J | -0.020 |
ulu | -0.020 |
ory | -0.019 |
common | -0.019 |
Ar | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
oved | +0.031 |
opes | +0.031 |
zed | +0.029 |
iously | +0.029 |
sed | +0.029 |
Neg logit contributions | |
ory | -0.024 |
ulu | -0.024 |
J | -0.023 |
Jill | -0.022 |
common | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
oved | +0.076 |
zed | +0.075 |
opes | +0.073 |
ths | +0.070 |
iously | +0.069 |
Neg logit contributions | |
ulu | -0.051 |
J | -0.049 |
ory | -0.049 |
common | -0.044 |
Jill | -0.043 |
Token | m |
Token ID | 285 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
oved | +0.107 |
zed | +0.104 |
opes | +0.102 |
iously | +0.097 |
ths | +0.097 |
Neg logit contributions | |
ulu | -0.056 |
J | -0.054 |
ory | -0.054 |
Jill | -0.049 |
common | -0.047 |
Token | ule |
Token ID | 2261 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
zed | +0.139 |
oved | +0.131 |
opes | +0.125 |
sed | +0.122 |
ths | +0.116 |
Neg logit contributions | |
ulu | -0.184 |
ory | -0.184 |
J | -0.174 |
ola | -0.161 |
ora | -0.157 |
Token | were |
Token ID | 547 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
oved | +0.189 |
iously | +0.184 |
opes | +0.182 |
zed | +0.178 |
sed | +0.174 |
Neg logit contributions | |
ulu | -0.145 |
ory | -0.138 |
J | -0.137 |
Jill | -0.131 |
ola | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
oved | +0.078 |
opes | +0.077 |
sed | +0.076 |
iously | +0.074 |
zed | +0.072 |
Neg logit contributions | |
ulu | -0.054 |
J | -0.052 |
Jill | -0.049 |
ory | -0.049 |
common | -0.046 |
Token | best |
Token ID | 1266 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
oved | +0.050 |
zed | +0.047 |
opes | +0.046 |
ths | +0.044 |
iously | +0.043 |
Neg logit contributions | |
ulu | -0.071 |
J | -0.069 |
ory | -0.069 |
Jill | -0.065 |
common | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
opes | +0.036 |
oved | +0.036 |
zed | +0.036 |
sed | +0.034 |
iously | +0.034 |
Neg logit contributions | |
ulu | -0.022 |
ory | -0.021 |
J | -0.020 |
Jill | -0.019 |
ola | -0.018 |
Token | pen |
Token ID | 3112 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
oved | +0.043 |
zed | +0.043 |
opes | +0.042 |
ths | +0.040 |
iously | +0.039 |
Neg logit contributions | |
ulu | -0.046 |
ory | -0.045 |
common | -0.043 |
J | -0.042 |
Jill | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
opes | +0.062 |
zed | +0.062 |
ths | +0.061 |
oved | +0.060 |
iously | +0.060 |
Neg logit contributions | |
ulu | -0.036 |
J | -0.035 |
ory | -0.035 |
common | -0.031 |
Jill | -0.031 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ulu | +0.005 |
J | +0.005 |
Jill | +0.005 |
ory | +0.005 |
common | +0.005 |
Neg logit contributions | |
oved | -0.006 |
opes | -0.005 |
zed | -0.005 |
ths | -0.005 |
iously | -0.005 |
Token | â |
Token ID | 22940 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
oved | +0.041 |
opes | +0.039 |
zed | +0.039 |
ths | +0.037 |
iously | +0.037 |
Neg logit contributions | |
ulu | -0.052 |
J | -0.050 |
ory | -0.049 |
common | -0.047 |
Jill | -0.047 |
Token | € |
Token ID | 26391 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
oved | +0.039 |
zed | +0.038 |
opes | +0.035 |
ths | +0.033 |
iously | +0.033 |
Neg logit contributions | |
ulu | -0.047 |
ory | -0.046 |
J | -0.045 |
Jill | -0.042 |
common | -0.042 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
iously | +0.052 |
der | +0.046 |
oved | +0.046 |
opes | +0.046 |
ths | +0.044 |
Neg logit contributions | |
J | -0.067 |
ulu | -0.055 |
L | -0.055 |
Jenny | -0.054 |
Jill | -0.053 |
Token | t |
Token ID | 83 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
oved | +0.161 |
zed | +0.155 |
opes | +0.152 |
ths | +0.142 |
iously | +0.141 |
Neg logit contributions | |
ulu | -0.176 |
J | -0.171 |
ory | -0.170 |
common | -0.159 |
Jill | -0.158 |
Token | know |
Token ID | 760 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
zed | +0.017 |
oved | +0.017 |
opes | +0.015 |
erved | +0.015 |
aged | +0.015 |
Neg logit contributions | |
ory | -0.015 |
ulu | -0.014 |
J | -0.014 |
ora | -0.013 |
ola | -0.013 |
Token | where |
Token ID | 810 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
oved | +0.018 |
zed | +0.017 |
opes | +0.017 |
iously | +0.016 |
ths | +0.016 |
Neg logit contributions | |
ulu | -0.017 |
J | -0.017 |
ory | -0.016 |
Jill | -0.016 |
common | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ulu | +0.002 |
J | +0.002 |
ory | +0.002 |
common | +0.002 |
Jill | +0.002 |
Neg logit contributions | |
oved | -0.004 |
zed | -0.004 |
opes | -0.004 |
ths | -0.004 |
iously | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
oved | +0.008 |
opes | +0.008 |
zed | +0.008 |
iously | +0.008 |
ths | +0.008 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.004 |
ory | -0.004 |
Jill | -0.004 |
common | -0.004 |
Token | wealthy |
Token ID | 11574 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
oved | +0.017 |
zed | +0.017 |
ths | +0.017 |
opes | +0.017 |
iously | +0.016 |
Neg logit contributions | |
ulu | -0.017 |
J | -0.016 |
common | -0.016 |
ory | -0.016 |
Jill | -0.016 |
Token | prince |
Token ID | 19716 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
oved | +0.016 |
zed | +0.016 |
opes | +0.015 |
ths | +0.015 |
iously | +0.015 |
Neg logit contributions | |
ulu | -0.012 |
J | -0.011 |
common | -0.010 |
Jill | -0.010 |
ory | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
oved | +0.024 |
opes | +0.023 |
zed | +0.023 |
iously | +0.021 |
ths | +0.021 |
Neg logit contributions | |
ulu | -0.018 |
ory | -0.018 |
J | -0.018 |
Jill | -0.016 |
common | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
zed | +0.042 |
oved | +0.039 |
meanings | +0.039 |
iously | +0.038 |
opes | +0.037 |
Neg logit contributions | |
ulu | -0.039 |
J | -0.039 |
ory | -0.038 |
ola | -0.036 |
oe | -0.035 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
oved | +0.078 |
zed | +0.076 |
opes | +0.075 |
ths | +0.071 |
iously | +0.071 |
Neg logit contributions | |
ulu | -0.060 |
J | -0.059 |
ory | -0.058 |
common | -0.053 |
Jill | -0.053 |
Token | fl |
Token ID | 2704 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
oved | +0.056 |
zed | +0.054 |
opes | +0.053 |
iously | +0.051 |
ths | +0.050 |
Neg logit contributions | |
ulu | -0.039 |
ory | -0.037 |
J | -0.036 |
Jill | -0.033 |
common | -0.033 |
Token | owers |
Token ID | 3618 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
zed | +0.127 |
oved | +0.117 |
opes | +0.108 |
iously | +0.107 |
erved | +0.104 |
Neg logit contributions | |
ulu | -0.209 |
ory | -0.206 |
J | -0.190 |
ora | -0.186 |
ola | -0.185 |
Token | lived |
Token ID | 5615 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
oved | +0.087 |
zed | +0.085 |
opes | +0.084 |
iously | +0.080 |
erved | +0.079 |
Neg logit contributions | |
ulu | -0.067 |
ory | -0.064 |
J | -0.061 |
common | -0.058 |
Jill | -0.057 |
Token | happily |
Token ID | 18177 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ulu | +0.007 |
ory | +0.007 |
J | +0.007 |
common | +0.006 |
Jill | +0.006 |
Neg logit contributions | |
oved | -0.007 |
zed | -0.006 |
opes | -0.006 |
ths | -0.006 |
iously | -0.006 |
Token | ever |
Token ID | 1683 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
oved | +0.051 |
opes | +0.051 |
zed | +0.051 |
ths | +0.047 |
erved | +0.046 |
Neg logit contributions | |
ulu | -0.038 |
ory | -0.038 |
J | -0.036 |
common | -0.033 |
Jill | -0.033 |
Token | after |
Token ID | 706 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.022 |
opes | +0.022 |
iously | +0.021 |
ths | +0.021 |
Neg logit contributions | |
ulu | -0.027 |
J | -0.025 |
ory | -0.024 |
Jill | -0.023 |
common | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ulu | +0.006 |
ory | +0.006 |
J | +0.006 |
Jill | +0.006 |
common | +0.006 |
Neg logit contributions | |
oved | -0.007 |
opes | -0.007 |
zed | -0.007 |
ths | -0.007 |
iously | -0.007 |
Token | smarter |
Token ID | 23714 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
oved | +0.009 |
zed | +0.008 |
opes | +0.008 |
ths | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.009 |
ory | -0.008 |
J | -0.008 |
common | -0.008 |
Jill | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ulu | +0.013 |
J | +0.013 |
ory | +0.013 |
common | +0.012 |
Jill | +0.012 |
Neg logit contributions | |
oved | -0.020 |
zed | -0.020 |
opes | -0.019 |
ths | -0.018 |
iously | -0.018 |
Token | In |
Token ID | 554 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
oved | +0.009 |
zed | +0.009 |
opes | +0.009 |
ths | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.009 |
J | -0.009 |
ory | -0.009 |
common | -0.008 |
Jill | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ulu | +0.010 |
ory | +0.010 |
J | +0.009 |
Jill | +0.008 |
ora | +0.008 |
Neg logit contributions | |
oved | -0.014 |
zed | -0.014 |
opes | -0.013 |
ths | -0.013 |
iously | -0.012 |
Token | end |
Token ID | 886 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
ulu | +0.010 |
ory | +0.010 |
J | +0.009 |
emo | +0.009 |
ola | +0.009 |
Neg logit contributions | |
oved | -0.011 |
zed | -0.011 |
opes | -0.010 |
ths | -0.010 |
erved | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ory | +0.113 |
ulu | +0.111 |
J | +0.106 |
common | +0.099 |
ora | +0.098 |
Neg logit contributions | |
oved | -0.102 |
zed | -0.101 |
opes | -0.096 |
ths | -0.094 |
iously | -0.089 |
Token | he |
Token ID | 339 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ulu | +0.008 |
ory | +0.008 |
J | +0.008 |
common | +0.007 |
ora | +0.007 |
Neg logit contributions | |
zed | -0.010 |
oved | -0.010 |
opes | -0.010 |
ths | -0.009 |
iously | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
oved | +0.006 |
zed | +0.006 |
opes | +0.006 |
ths | +0.006 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
ory | -0.006 |
common | -0.005 |
Jill | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
oved | +0.005 |
opes | +0.005 |
zed | +0.005 |
ths | +0.004 |
iously | +0.004 |
Neg logit contributions | |
J | -0.005 |
ulu | -0.005 |
ory | -0.005 |
Jill | -0.005 |
common | -0.005 |
Token | word |
Token ID | 1573 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ulu | +0.014 |
ory | +0.014 |
J | +0.013 |
ola | +0.012 |
Jill | +0.012 |
Neg logit contributions | |
oved | -0.014 |
zed | -0.014 |
ths | -0.013 |
opes | -0.013 |
sed | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
ulu | +0.015 |
ory | +0.015 |
J | +0.014 |
common | +0.014 |
ora | +0.013 |
Neg logit contributions | |
zed | -0.018 |
oved | -0.018 |
opes | -0.017 |
ths | -0.017 |
sed | -0.016 |
Token | all |
Token ID | 477 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
oved | +0.013 |
zed | +0.013 |
opes | +0.012 |
ths | +0.011 |
sed | +0.011 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.014 |
ory | -0.013 |
common | -0.013 |
Jill | -0.012 |
Token | had |
Token ID | 550 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ulu | +0.010 |
J | +0.010 |
ory | +0.010 |
common | +0.009 |
Jill | +0.009 |
Neg logit contributions | |
oved | -0.011 |
zed | -0.011 |
opes | -0.011 |
ths | -0.010 |
iously | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
J | +0.004 |
ulu | +0.004 |
ory | +0.004 |
Jill | +0.004 |
common | +0.004 |
Neg logit contributions | |
oved | -0.006 |
zed | -0.006 |
opes | -0.006 |
iously | -0.006 |
ths | -0.006 |
Token | great |
Token ID | 1049 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.005 |
sed | +0.005 |
ths | +0.005 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.005 |
ory | -0.005 |
Jill | -0.005 |
ola | -0.005 |
Token | time |
Token ID | 640 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
ulu | +0.016 |
J | +0.016 |
ory | +0.015 |
Jill | +0.014 |
common | +0.014 |
Neg logit contributions | |
oved | -0.019 |
zed | -0.018 |
opes | -0.018 |
ths | -0.017 |
iously | -0.017 |
Token | playing |
Token ID | 2712 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ulu | +0.087 |
J | +0.085 |
ory | +0.084 |
Jill | +0.079 |
common | +0.077 |
Neg logit contributions | |
oved | -0.121 |
zed | -0.119 |
opes | -0.118 |
ths | -0.112 |
iously | -0.111 |
Token | games |
Token ID | 1830 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ulu | +0.010 |
J | +0.010 |
ory | +0.010 |
common | +0.009 |
Jill | +0.009 |
Neg logit contributions | |
oved | -0.013 |
zed | -0.013 |
opes | -0.013 |
ths | -0.012 |
iously | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
ulu | +0.034 |
J | +0.033 |
ory | +0.033 |
common | +0.030 |
Jill | +0.030 |
Neg logit contributions | |
oved | -0.052 |
zed | -0.050 |
opes | -0.050 |
ths | -0.047 |
iously | -0.047 |
Token | eating |
Token ID | 6600 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
ory | +0.024 |
ulu | +0.024 |
J | +0.023 |
common | +0.022 |
ora | +0.022 |
Neg logit contributions | |
zed | -0.014 |
oved | -0.013 |
opes | -0.013 |
ths | -0.012 |
sed | -0.011 |
Token | cake |
Token ID | 12187 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
oved | +0.030 |
zed | +0.029 |
opes | +0.029 |
ths | +0.026 |
iously | +0.026 |
Neg logit contributions | |
ulu | -0.033 |
ory | -0.031 |
J | -0.031 |
ola | -0.029 |
ora | -0.028 |
Token | Then |
Token ID | 3244 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
ulu | +0.007 |
ory | +0.007 |
J | +0.007 |
common | +0.007 |
deeper | +0.007 |
Neg logit contributions | |
Leave | -0.004 |
oved | -0.004 |
opes | -0.003 |
zed | -0.003 |
der | -0.003 |
Token | give |
Token ID | 1577 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ulu | +0.029 |
J | +0.029 |
ory | +0.027 |
common | +0.025 |
emo | +0.025 |
Neg logit contributions | |
zed | -0.025 |
ths | -0.023 |
iously | -0.023 |
oved | -0.023 |
opes | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ulu | +0.088 |
opener | +0.083 |
J | +0.081 |
common | +0.078 |
ory | +0.076 |
Neg logit contributions | |
zed | -0.084 |
oved | -0.079 |
iously | -0.074 |
ths | -0.074 |
erved | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
oved | +0.009 |
zed | +0.009 |
opes | +0.009 |
erved | +0.008 |
iously | +0.008 |
Neg logit contributions | |
ulu | -0.011 |
J | -0.011 |
ory | -0.011 |
common | -0.010 |
ola | -0.010 |
Token | someone |
Token ID | 2130 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
zed | +0.017 |
oved | +0.016 |
opes | +0.016 |
ow | +0.016 |
iously | +0.016 |
Neg logit contributions | |
J | -0.011 |
ulu | -0.011 |
ory | -0.011 |
common | -0.010 |
opener | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ulu | +0.061 |
J | +0.060 |
ory | +0.058 |
common | +0.054 |
Jill | +0.053 |
Neg logit contributions | |
oved | -0.049 |
zed | -0.046 |
opes | -0.044 |
iously | -0.042 |
ths | -0.042 |
Token | like |
Token ID | 588 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ulu | +0.090 |
J | +0.086 |
ory | +0.084 |
common | +0.078 |
Jill | +0.077 |
Neg logit contributions | |
oved | -0.118 |
zed | -0.113 |
opes | -0.112 |
iously | -0.105 |
ths | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
ulu | +0.058 |
J | +0.056 |
ory | +0.055 |
common | +0.051 |
Jill | +0.050 |
Neg logit contributions | |
oved | -0.071 |
zed | -0.068 |
opes | -0.068 |
ths | -0.064 |
iously | -0.064 |
Token | They |
Token ID | 1119 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ulu | +0.003 |
ory | +0.003 |
J | +0.003 |
ora | +0.003 |
deeper | +0.003 |
Neg logit contributions | |
Leave | -0.002 |
oved | -0.001 |
opes | -0.001 |
zed | -0.001 |
der | -0.001 |
Token | will |
Token ID | 481 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ulu | +0.004 |
J | +0.004 |
ory | +0.003 |
Jill | +0.003 |
common | +0.003 |
Neg logit contributions | |
oved | -0.005 |
opes | -0.005 |
zed | -0.005 |
ths | -0.004 |
iously | -0.004 |
Token | be |
Token ID | 307 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ulu | +0.011 |
ory | +0.011 |
J | +0.011 |
Jill | +0.010 |
ola | +0.010 |
Neg logit contributions | |
oved | -0.013 |
opes | -0.012 |
zed | -0.012 |
ths | -0.011 |
iously | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ulu | +0.022 |
J | +0.021 |
ory | +0.020 |
Jill | +0.019 |
common | +0.019 |
Neg logit contributions | |
oved | -0.038 |
zed | -0.038 |
opes | -0.037 |
ths | -0.036 |
iously | -0.035 |
Token | It |
Token ID | 632 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ulu | +0.022 |
ory | +0.022 |
J | +0.022 |
common | +0.020 |
Jill | +0.020 |
Neg logit contributions | |
oved | -0.015 |
zed | -0.014 |
opes | -0.014 |
iously | -0.013 |
ths | -0.012 |
Token | says |
Token ID | 1139 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ory | +0.056 |
ulu | +0.055 |
J | +0.055 |
ola | +0.048 |
Jill | +0.048 |
Neg logit contributions | |
oved | -0.047 |
opes | -0.044 |
zed | -0.044 |
ths | -0.041 |
sed | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ulu | +0.048 |
J | +0.047 |
ory | +0.047 |
common | +0.044 |
Jill | +0.043 |
Neg logit contributions | |
oved | -0.047 |
zed | -0.045 |
opes | -0.044 |
ths | -0.041 |
iously | -0.041 |
Token | " |
Token ID | 366 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
oved | +0.003 |
zed | +0.003 |
opes | +0.003 |
ths | +0.003 |
iously | +0.003 |
Neg logit contributions | |
ulu | -0.004 |
J | -0.004 |
ory | -0.004 |
Jill | -0.003 |
common | -0.003 |
Token | Join |
Token ID | 18234 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
oved | +0.030 |
zed | +0.027 |
ths | +0.027 |
opes | +0.027 |
ending | +0.026 |
Neg logit contributions | |
ulu | -0.026 |
ory | -0.025 |
common | -0.023 |
Jill | -0.023 |
J | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
ulu | +0.111 |
ory | +0.107 |
J | +0.101 |
ola | +0.090 |
Jill | +0.089 |
Neg logit contributions | |
oved | -0.117 |
opes | -0.117 |
zed | -0.113 |
ths | -0.108 |
meanings | -0.104 |
Token | Jazz |
Token ID | 21406 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
ulu | +0.000 |
ory | +0.000 |
J | +0.000 |
ackers | +0.000 |
emo | +0.000 |
Neg logit contributions | |
oved | -0.000 |
opes | -0.000 |
meanings | -0.000 |
zed | -0.000 |
sed | -0.000 |
Token | Club |
Token ID | 6289 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ulu | +0.025 |
J | +0.024 |
ory | +0.024 |
Jill | +0.022 |
common | +0.022 |
Neg logit contributions | |
oved | -0.032 |
zed | -0.031 |
opes | -0.031 |
ths | -0.029 |
iously | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
ulu | +0.059 |
J | +0.057 |
ory | +0.057 |
common | +0.052 |
Jill | +0.050 |
Neg logit contributions | |
oved | -0.065 |
opes | -0.060 |
zed | -0.060 |
ths | -0.056 |
iously | -0.056 |
Token | Learn |
Token ID | 14365 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
oved | +0.018 |
Leave | +0.018 |
opes | +0.016 |
zed | +0.016 |
chair | +0.015 |
Neg logit contributions | |
ulu | -0.035 |
ory | -0.034 |
common | -0.032 |
J | -0.032 |
ackers | -0.030 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
ulu | +0.013 |
ory | +0.011 |
J | +0.011 |
Jill | +0.011 |
ola | +0.011 |
Neg logit contributions | |
oved | -0.019 |
opes | -0.019 |
zed | -0.019 |
ths | -0.018 |
sed | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
ulu | +0.014 |
ory | +0.013 |
J | +0.013 |
common | +0.013 |
ola | +0.011 |
Neg logit contributions | |
oved | -0.017 |
zed | -0.017 |
opes | -0.016 |
iously | -0.016 |
ths | -0.015 |
Token | jumped |
Token ID | 11687 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ulu | +0.007 |
J | +0.007 |
ory | +0.007 |
common | +0.007 |
Jill | +0.006 |
Neg logit contributions | |
oved | -0.009 |
zed | -0.009 |
opes | -0.009 |
ths | -0.008 |
iously | -0.008 |
Token | into |
Token ID | 656 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ulu | +0.006 |
J | +0.005 |
common | +0.005 |
ory | +0.005 |
ola | +0.005 |
Neg logit contributions | |
oved | -0.004 |
zed | -0.004 |
iously | -0.004 |
opes | -0.004 |
ze | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
zed | +0.007 |
iously | +0.007 |
ow | +0.006 |
opes | +0.006 |
oved | +0.006 |
Neg logit contributions | |
ory | -0.009 |
ulu | -0.009 |
J | -0.008 |
ora | -0.008 |
emo | -0.008 |
Token | cool |
Token ID | 3608 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
J | +0.030 |
ory | +0.029 |
common | +0.028 |
ulu | +0.028 |
Jill | +0.027 |
Neg logit contributions | |
zed | -0.034 |
oved | -0.033 |
opes | -0.032 |
iously | -0.031 |
ow | -0.031 |
Token | water |
Token ID | 1660 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
J | +0.109 |
ulu | +0.091 |
common | +0.091 |
Col | +0.088 |
ory | +0.087 |
Neg logit contributions | |
oved | -0.109 |
iously | -0.109 |
opes | -0.107 |
zed | -0.106 |
ow | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ulu | +0.061 |
J | +0.061 |
ory | +0.058 |
common | +0.056 |
Jill | +0.053 |
Neg logit contributions | |
oved | -0.068 |
zed | -0.065 |
opes | -0.065 |
iously | -0.062 |
ths | -0.061 |
Token | started |
Token ID | 2067 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ulu | +0.020 |
ory | +0.020 |
J | +0.020 |
common | +0.019 |
ola | +0.018 |
Neg logit contributions | |
zed | -0.021 |
oved | -0.020 |
opes | -0.019 |
ths | -0.019 |
iously | -0.019 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
ory | +0.007 |
ulu | +0.006 |
J | +0.006 |
common | +0.006 |
ola | +0.006 |
Neg logit contributions | |
zed | -0.006 |
oved | -0.006 |
opes | -0.006 |
ze | -0.006 |
iously | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
oved | +0.045 |
opes | +0.044 |
iously | +0.043 |
ths | +0.041 |
zed | +0.040 |
Neg logit contributions | |
ulu | -0.065 |
J | -0.064 |
ory | -0.062 |
common | -0.059 |
ola | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
J | +0.001 |
ulu | +0.001 |
ory | +0.001 |
Jill | +0.001 |
Jenny | +0.001 |
Neg logit contributions | |
oved | -0.002 |
opes | -0.002 |
zed | -0.001 |
iously | -0.001 |
ths | -0.001 |
Token | wear |
Token ID | 5806 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ulu | +0.024 |
J | +0.023 |
ory | +0.023 |
common | +0.021 |
Jill | +0.020 |
Neg logit contributions | |
zed | -0.031 |
oved | -0.031 |
opes | -0.029 |
erved | -0.027 |
ow | -0.027 |
Token | all |
Token ID | 477 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
ulu | +0.055 |
J | +0.053 |
ory | +0.053 |
Jill | +0.049 |
common | +0.048 |
Neg logit contributions | |
oved | -0.064 |
zed | -0.062 |
opes | -0.061 |
ths | -0.057 |
iously | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
oved | +0.026 |
zed | +0.025 |
opes | +0.023 |
chair | +0.022 |
about | +0.022 |
Neg logit contributions | |
ory | -0.028 |
J | -0.027 |
ulu | -0.027 |
common | -0.025 |
Col | -0.024 |
Token | time |
Token ID | 640 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
oved | +0.027 |
opes | +0.026 |
zed | +0.025 |
meanings | +0.024 |
ow | +0.023 |
Neg logit contributions | |
ulu | -0.025 |
ory | -0.024 |
J | -0.024 |
Jill | -0.023 |
ola | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
ulu | +0.069 |
ory | +0.066 |
J | +0.066 |
common | +0.060 |
Jill | +0.059 |
Neg logit contributions | |
oved | -0.102 |
zed | -0.098 |
opes | -0.097 |
ths | -0.092 |
iously | -0.091 |
Token | One |
Token ID | 1881 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
ulu | +0.000 |
J | +0.000 |
ory | +0.000 |
common | +0.000 |
Jill | +0.000 |
Neg logit contributions | |
oved | -0.000 |
zed | -0.000 |
opes | -0.000 |
ths | -0.000 |
iously | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ulu | +0.016 |
J | +0.015 |
ory | +0.015 |
common | +0.014 |
Jill | +0.014 |
Neg logit contributions | |
oved | -0.021 |
zed | -0.020 |
opes | -0.019 |
ths | -0.018 |
iously | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.007 |
opes | +0.007 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
Jill | -0.004 |
common | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.023 |
opes | +0.022 |
ths | +0.021 |
sed | +0.021 |
Neg logit contributions | |
ulu | -0.009 |
ory | -0.009 |
J | -0.008 |
common | -0.008 |
ora | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ulu | +0.041 |
J | +0.040 |
ory | +0.040 |
common | +0.037 |
Jill | +0.037 |
Neg logit contributions | |
oved | -0.047 |
zed | -0.045 |
opes | -0.045 |
ths | -0.042 |
iously | -0.042 |
Token | show |
Token ID | 905 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
oved | +0.004 |
zed | +0.004 |
opes | +0.004 |
ow | +0.003 |
ze | +0.003 |
Neg logit contributions | |
J | -0.004 |
ory | -0.004 |
ulu | -0.004 |
Col | -0.003 |
ora | -0.003 |
Token | me |
Token ID | 502 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ulu | +0.037 |
J | +0.036 |
ory | +0.035 |
common | +0.032 |
Jill | +0.031 |
Neg logit contributions | |
oved | -0.042 |
opes | -0.041 |
zed | -0.041 |
ths | -0.038 |
iously | -0.037 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
J | +0.006 |
ulu | +0.006 |
ory | +0.006 |
common | +0.005 |
Jill | +0.005 |
Neg logit contributions | |
oved | -0.008 |
zed | -0.007 |
opes | -0.007 |
ths | -0.007 |
iously | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
ulu | +0.022 |
ory | +0.022 |
J | +0.022 |
common | +0.020 |
Jill | +0.020 |
Neg logit contributions | |
oved | -0.022 |
zed | -0.022 |
opes | -0.021 |
iously | -0.020 |
ths | -0.020 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
ulu | +0.027 |
ory | +0.027 |
J | +0.026 |
common | +0.024 |
Jill | +0.024 |
Neg logit contributions | |
oved | -0.036 |
opes | -0.035 |
zed | -0.035 |
ths | -0.034 |
sed | -0.033 |
Token | said |
Token ID | 531 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
ulu | +0.018 |
J | +0.018 |
ory | +0.017 |
common | +0.016 |
Jill | +0.016 |
Neg logit contributions | |
oved | -0.028 |
zed | -0.027 |
opes | -0.027 |
ths | -0.026 |
iously | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ulu | +0.012 |
J | +0.012 |
ory | +0.012 |
common | +0.011 |
Jill | +0.011 |
Neg logit contributions | |
oved | -0.016 |
zed | -0.016 |
opes | -0.016 |
ths | -0.015 |
iously | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
oved | +0.012 |
opes | +0.011 |
zed | +0.011 |
erved | +0.011 |
ths | +0.010 |
Neg logit contributions | |
J | -0.010 |
ulu | -0.010 |
ory | -0.010 |
Jill | -0.010 |
mer | -0.009 |
Token | Follow |
Token ID | 7155 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
oved | +0.037 |
zed | +0.035 |
opes | +0.035 |
ths | +0.033 |
meanings | +0.032 |
Neg logit contributions | |
ory | -0.035 |
ulu | -0.035 |
Jill | -0.033 |
J | -0.033 |
common | -0.031 |
Token | me |
Token ID | 502 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
ulu | +0.052 |
ory | +0.050 |
J | +0.050 |
ola | +0.045 |
common | +0.044 |
Neg logit contributions | |
opes | -0.043 |
zed | -0.041 |
oved | -0.041 |
iously | -0.040 |
ths | -0.039 |
Token | He |
Token ID | 679 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
oved | +0.002 |
zed | +0.002 |
opes | +0.002 |
sed | +0.002 |
erved | +0.002 |
Neg logit contributions | |
ulu | -0.003 |
ory | -0.003 |
J | -0.003 |
ora | -0.002 |
ola | -0.002 |
Token | picked |
Token ID | 6497 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
oved | +0.008 |
zed | +0.007 |
opes | +0.007 |
ths | +0.007 |
iously | +0.007 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
ory | -0.006 |
common | -0.006 |
Jill | -0.006 |
Token | up |
Token ID | 510 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ulu | +0.024 |
J | +0.023 |
common | +0.022 |
ory | +0.022 |
ola | +0.020 |
Neg logit contributions | |
oved | -0.011 |
zed | -0.011 |
erved | -0.010 |
iously | -0.009 |
opes | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
zed | +0.013 |
oved | +0.013 |
erved | +0.013 |
opes | +0.012 |
ow | +0.012 |
Neg logit contributions | |
ulu | -0.020 |
ory | -0.019 |
ora | -0.018 |
ola | -0.018 |
Ar | -0.018 |
Token | fork |
Token ID | 15563 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ulu | +0.001 |
J | +0.001 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
iously | -0.001 |
sed | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
oved | +0.040 |
zed | +0.037 |
opes | +0.037 |
iously | +0.036 |
ths | +0.035 |
Neg logit contributions | |
ulu | -0.036 |
J | -0.035 |
ory | -0.034 |
common | -0.033 |
Jill | -0.031 |
Token | took |
Token ID | 1718 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ulu | +0.029 |
ory | +0.027 |
J | +0.027 |
ola | +0.025 |
common | +0.025 |
Neg logit contributions | |
zed | -0.033 |
oved | -0.031 |
opes | -0.031 |
sed | -0.029 |
ths | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
zed | +0.008 |
oved | +0.007 |
erved | +0.007 |
ze | +0.007 |
aged | +0.007 |
Neg logit contributions | |
ulu | -0.010 |
ory | -0.010 |
ora | -0.009 |
J | -0.009 |
common | -0.008 |
Token | small |
Token ID | 1402 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ulu | +0.028 |
J | +0.028 |
rust | +0.027 |
ory | +0.027 |
Jill | +0.026 |
Neg logit contributions | |
zed | -0.031 |
chair | -0.029 |
oved | -0.029 |
ow | -0.028 |
zing | -0.027 |
Token | bite |
Token ID | 13197 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
ulu | +0.035 |
J | +0.033 |
ory | +0.031 |
Jill | +0.030 |
ola | +0.030 |
Neg logit contributions | |
oved | -0.035 |
zed | -0.031 |
chair | -0.031 |
sed | -0.031 |
ze | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ulu | +0.032 |
ory | +0.031 |
common | +0.031 |
J | +0.031 |
Col | +0.028 |
Neg logit contributions | |
oved | -0.027 |
der | -0.024 |
zed | -0.024 |
iously | -0.022 |
chair | -0.022 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
J | +0.051 |
ulu | +0.050 |
ory | +0.046 |
common | +0.046 |
ola | +0.044 |
Neg logit contributions | |
oved | -0.072 |
sed | -0.070 |
ths | -0.070 |
chair | -0.069 |
ow | -0.067 |
Token | found |
Token ID | 1043 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ulu | +0.037 |
ory | +0.036 |
J | +0.035 |
common | +0.034 |
Jill | +0.032 |
Neg logit contributions | |
oved | -0.046 |
zed | -0.044 |
opes | -0.043 |
ths | -0.041 |
iously | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ory | +0.005 |
ulu | +0.005 |
J | +0.005 |
common | +0.005 |
ola | +0.004 |
Neg logit contributions | |
oved | -0.006 |
zed | -0.006 |
opes | -0.006 |
iously | -0.006 |
ths | -0.006 |
Token | tough |
Token ID | 5802 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ulu | +0.000 |
J | +0.000 |
ory | +0.000 |
common | +0.000 |
Jill | +0.000 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | magnet |
Token ID | 19972 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
oved | +0.016 |
opes | +0.016 |
zed | +0.015 |
iously | +0.015 |
ths | +0.014 |
Neg logit contributions | |
ulu | -0.013 |
J | -0.012 |
ory | -0.012 |
common | -0.011 |
ola | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ulu | +0.006 |
ory | +0.006 |
J | +0.006 |
Jill | +0.006 |
ola | +0.005 |
Neg logit contributions | |
zed | -0.012 |
oved | -0.012 |
opes | -0.012 |
ths | -0.011 |
erved | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Jill | +0.015 |
J | +0.014 |
ory | +0.014 |
ulu | +0.014 |
Jenny | +0.014 |
Neg logit contributions | |
oved | -0.020 |
zed | -0.020 |
opes | -0.020 |
ths | -0.019 |
sed | -0.018 |
Token | Hello |
Token ID | 15496 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
oved | +0.041 |
ths | +0.037 |
zed | +0.037 |
opes | +0.035 |
ending | +0.033 |
Neg logit contributions | |
ulu | -0.053 |
ory | -0.051 |
common | -0.048 |
Jill | -0.047 |
ola | -0.047 |
Token | ," |
Token ID | 553 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
ulu | +0.052 |
ory | +0.051 |
J | +0.050 |
Jill | +0.046 |
common | +0.046 |
Neg logit contributions | |
oved | -0.078 |
zed | -0.076 |
opes | -0.075 |
iously | -0.070 |
ths | -0.070 |
Token | she |
Token ID | 673 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
ulu | +0.023 |
ory | +0.022 |
J | +0.022 |
common | +0.020 |
ola | +0.019 |
Neg logit contributions | |
oved | -0.029 |
zed | -0.029 |
opes | -0.028 |
ths | -0.028 |
iously | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ulu | +0.010 |
ory | +0.010 |
J | +0.010 |
common | +0.009 |
ola | +0.009 |
Neg logit contributions | |
oved | -0.013 |
zed | -0.012 |
opes | -0.012 |
iously | -0.012 |
sed | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
ulu | +0.053 |
J | +0.051 |
ory | +0.051 |
Jill | +0.046 |
common | +0.046 |
Neg logit contributions | |
oved | -0.086 |
zed | -0.083 |
opes | -0.082 |
ths | -0.078 |
iously | -0.078 |
Token | They |
Token ID | 1119 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
oved | +0.012 |
zed | +0.012 |
opes | +0.011 |
ths | +0.011 |
iously | +0.011 |
Neg logit contributions | |
ulu | -0.009 |
ory | -0.009 |
J | -0.009 |
common | -0.008 |
Jill | -0.008 |
Token | hope |
Token ID | 2911 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
oved | +0.011 |
zed | +0.011 |
opes | +0.011 |
ths | +0.010 |
iously | +0.010 |
Neg logit contributions | |
ulu | -0.007 |
J | -0.007 |
ory | -0.006 |
Jill | -0.006 |
common | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
oved | +0.032 |
zed | +0.031 |
opes | +0.030 |
ths | +0.029 |
iously | +0.029 |
Neg logit contributions | |
ulu | -0.019 |
ory | -0.018 |
J | -0.018 |
common | -0.016 |
Jill | -0.016 |
Token | mosquito |
Token ID | 35446 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
oved | +0.013 |
opes | +0.012 |
zed | +0.012 |
iously | +0.012 |
ths | +0.011 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.013 |
ory | -0.012 |
common | -0.012 |
Jill | -0.012 |
Token | does |
Token ID | 857 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
oved | +0.059 |
opes | +0.057 |
zed | +0.056 |
iously | +0.054 |
ths | +0.054 |
Neg logit contributions | |
ulu | -0.037 |
ory | -0.035 |
J | -0.035 |
common | -0.033 |
Jill | -0.031 |
Token | not |
Token ID | 407 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ulu | +0.038 |
ory | +0.038 |
J | +0.036 |
ola | +0.035 |
Jill | +0.034 |
Neg logit contributions | |
zed | -0.023 |
oved | -0.022 |
opes | -0.020 |
erved | -0.019 |
ths | -0.019 |
Token | come |
Token ID | 1282 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
J | +0.009 |
ulu | +0.009 |
ory | +0.009 |
ola | +0.009 |
Col | +0.008 |
Neg logit contributions | |
oved | -0.007 |
ow | -0.007 |
ze | -0.007 |
opes | -0.007 |
zed | -0.007 |
Token | back |
Token ID | 736 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ulu | +0.002 |
J | +0.001 |
ory | +0.001 |
ola | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.001 |
opes | -0.001 |
zed | -0.001 |
erved | -0.001 |
iously | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.005 |
ths | +0.004 |
iously | +0.004 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
common | -0.003 |
Jill | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
oved | +0.010 |
zed | +0.010 |
opes | +0.010 |
sed | +0.009 |
erved | +0.009 |
Neg logit contributions | |
ulu | -0.010 |
ory | -0.009 |
J | -0.009 |
ola | -0.008 |
common | -0.008 |
Token | sauce |
Token ID | 10746 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
oved | +0.044 |
zed | +0.043 |
opes | +0.042 |
ths | +0.041 |
iously | +0.040 |
Neg logit contributions | |
ory | -0.030 |
ulu | -0.030 |
J | -0.029 |
common | -0.028 |
Jill | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
oved | +0.081 |
zed | +0.079 |
opes | +0.078 |
ths | +0.074 |
iously | +0.073 |
Neg logit contributions | |
ulu | -0.063 |
J | -0.061 |
ory | -0.061 |
Jill | -0.056 |
common | -0.056 |
Token | better |
Token ID | 1365 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
oved | +0.012 |
zed | +0.012 |
opes | +0.011 |
ths | +0.011 |
iously | +0.011 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.013 |
ory | -0.013 |
ora | -0.012 |
ola | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
ulu | +0.051 |
J | +0.050 |
ory | +0.049 |
common | +0.046 |
Jill | +0.046 |
Neg logit contributions | |
oved | -0.053 |
zed | -0.051 |
opes | -0.051 |
ths | -0.048 |
iously | -0.047 |
Token | They |
Token ID | 1119 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
oved | +0.016 |
zed | +0.016 |
opes | +0.015 |
iously | +0.014 |
ths | +0.014 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.014 |
ory | -0.014 |
common | -0.013 |
Jill | -0.012 |
Token | both |
Token ID | 1111 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
oved | +0.003 |
zed | +0.003 |
opes | +0.002 |
ths | +0.002 |
iously | +0.002 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
common | -0.002 |
Jill | -0.002 |
Token | felt |
Token ID | 2936 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
ulu | +0.003 |
J | +0.003 |
ory | +0.003 |
common | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
oved | -0.004 |
zed | -0.004 |
opes | -0.004 |
ths | -0.003 |
iously | -0.003 |
Token | angry |
Token ID | 7954 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
oved | +0.023 |
zed | +0.022 |
opes | +0.021 |
ths | +0.020 |
iously | +0.020 |
Neg logit contributions | |
ulu | -0.021 |
J | -0.021 |
ory | -0.020 |
common | -0.019 |
ola | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
zed | +0.125 |
oved | +0.123 |
opes | +0.120 |
ths | +0.114 |
sed | +0.112 |
Neg logit contributions | |
ory | -0.067 |
J | -0.067 |
ulu | -0.067 |
Jill | -0.066 |
Jenny | -0.061 |
Token | sad |
Token ID | 6507 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
oved | +0.012 |
zed | +0.011 |
opes | +0.011 |
ths | +0.011 |
iously | +0.011 |
Neg logit contributions | |
ulu | -0.012 |
J | -0.012 |
ory | -0.012 |
common | -0.011 |
Jill | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
oved | +0.032 |
zed | +0.031 |
opes | +0.031 |
ths | +0.029 |
erved | +0.029 |
Neg logit contributions | |
ory | -0.016 |
ulu | -0.016 |
Jill | -0.016 |
J | -0.016 |
Jenny | -0.015 |
Token | problem |
Token ID | 1917 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
oved | +0.052 |
zed | +0.050 |
opes | +0.049 |
iously | +0.047 |
ths | +0.047 |
Neg logit contributions | |
ulu | -0.048 |
J | -0.047 |
ory | -0.046 |
common | -0.042 |
Jill | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
oved | +0.016 |
zed | +0.015 |
opes | +0.015 |
ths | +0.014 |
iously | +0.014 |
Neg logit contributions | |
ulu | -0.011 |
ory | -0.010 |
J | -0.010 |
Jill | -0.010 |
common | -0.009 |
Token | just |
Token ID | 655 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
zed | +0.043 |
oved | +0.043 |
opes | +0.041 |
ths | +0.040 |
iously | +0.040 |
Neg logit contributions | |
ulu | -0.039 |
J | -0.039 |
ory | -0.037 |
common | -0.035 |
ora | -0.033 |
Token | be |
Token ID | 307 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ulu | +0.022 |
J | +0.022 |
ory | +0.022 |
common | +0.019 |
Jill | +0.019 |
Neg logit contributions | |
oved | -0.028 |
zed | -0.027 |
opes | -0.026 |
iously | -0.025 |
ths | -0.025 |
Token | careful |
Token ID | 8161 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ory | +0.045 |
ulu | +0.044 |
J | +0.042 |
common | +0.039 |
ora | +0.039 |
Neg logit contributions | |
zed | -0.035 |
oved | -0.035 |
ths | -0.032 |
opes | -0.031 |
ze | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
oved | +0.007 |
zed | +0.007 |
opes | +0.007 |
ths | +0.007 |
sed | +0.007 |
Neg logit contributions | |
ulu | -0.005 |
ory | -0.005 |
J | -0.005 |
Jill | -0.005 |
common | -0.004 |
Token | take |
Token ID | 1011 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.005 |
ths | +0.005 |
iously | +0.005 |
Neg logit contributions | |
ulu | -0.004 |
ory | -0.004 |
J | -0.004 |
common | -0.004 |
Jill | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
zed | +0.011 |
oved | +0.011 |
opes | +0.010 |
iously | +0.010 |
ths | +0.010 |
Neg logit contributions | |
ulu | -0.009 |
J | -0.008 |
ory | -0.008 |
Jill | -0.007 |
ola | -0.007 |
Token | easy |
Token ID | 2562 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
oved | +0.062 |
zed | +0.060 |
opes | +0.058 |
iously | +0.055 |
ths | +0.055 |
Neg logit contributions | |
ulu | -0.050 |
J | -0.049 |
ory | -0.048 |
common | -0.045 |
Jill | -0.044 |
Token | !" |
Token ID | 2474 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
oved | +0.019 |
zed | +0.018 |
opes | +0.018 |
ths | +0.017 |
sed | +0.017 |
Neg logit contributions | |
ulu | -0.015 |
ory | -0.015 |
J | -0.015 |
common | -0.014 |
Jill | -0.013 |
Token | |
Token ID | 220 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ulu | +0.015 |
ory | +0.015 |
J | +0.015 |
common | +0.014 |
Jill | +0.013 |
Neg logit contributions | |
oved | -0.024 |
zed | -0.024 |
opes | -0.023 |
iously | -0.022 |
ths | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
ory | +0.007 |
ulu | +0.007 |
J | +0.007 |
common | +0.006 |
ola | +0.006 |
Neg logit contributions | |
oved | -0.006 |
zed | -0.006 |
opes | -0.006 |
ths | -0.005 |
iously | -0.005 |
Token | k |
Token ID | 479 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
zed | +0.033 |
oved | +0.032 |
opes | +0.030 |
iously | +0.030 |
der | +0.028 |
Neg logit contributions | |
ulu | -0.019 |
common | -0.019 |
ory | -0.019 |
oe | -0.018 |
J | -0.017 |
Token | ites |
Token ID | 2737 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
oved | +0.018 |
zed | +0.018 |
opes | +0.017 |
iously | +0.016 |
ths | +0.016 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.014 |
ory | -0.014 |
common | -0.013 |
Jill | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
oved | +0.027 |
zed | +0.027 |
opes | +0.027 |
iously | +0.025 |
ths | +0.025 |
Neg logit contributions | |
ulu | -0.020 |
J | -0.019 |
ory | -0.019 |
Jill | -0.018 |
common | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ulu | +0.002 |
ory | +0.002 |
J | +0.002 |
ola | +0.001 |
common | +0.001 |
Neg logit contributions | |
zed | -0.002 |
oved | -0.002 |
opes | -0.002 |
sed | -0.002 |
ths | -0.002 |
Token | dolls |
Token ID | 36062 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
zed | +0.026 |
oved | +0.025 |
iously | +0.024 |
opes | +0.023 |
ending | +0.023 |
Neg logit contributions | |
common | -0.016 |
ulu | -0.015 |
ory | -0.015 |
J | -0.014 |
water | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
opes | +0.037 |
oved | +0.036 |
ths | +0.036 |
zed | +0.036 |
iously | +0.035 |
Neg logit contributions | |
ulu | -0.016 |
J | -0.015 |
ory | -0.014 |
Jill | -0.013 |
common | -0.013 |
Token | They |
Token ID | 1119 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
oved | +0.010 |
zed | +0.010 |
opes | +0.010 |
ths | +0.009 |
iously | +0.009 |
Neg logit contributions | |
ulu | -0.008 |
ory | -0.007 |
J | -0.007 |
common | -0.007 |
Jill | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
oved | +0.012 |
zed | +0.012 |
opes | +0.011 |
sed | +0.010 |
ths | +0.010 |
Neg logit contributions | |
ory | -0.011 |
ulu | -0.011 |
J | -0.011 |
common | -0.010 |
Jill | -0.010 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
oved | +0.027 |
zed | +0.026 |
opes | +0.026 |
ths | +0.025 |
iously | +0.025 |
Neg logit contributions | |
J | -0.014 |
ulu | -0.014 |
ory | -0.013 |
Jill | -0.013 |
common | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
J | +0.022 |
ulu | +0.021 |
mer | +0.020 |
common | +0.019 |
Jill | +0.018 |
Neg logit contributions | |
erved | -0.066 |
zed | -0.065 |
oved | -0.065 |
iously | -0.064 |
opes | -0.064 |
Token | ." |
Token ID | 526 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ory | +0.013 |
ulu | +0.013 |
J | +0.013 |
common | +0.012 |
Jill | +0.011 |
Neg logit contributions | |
zed | -0.026 |
oved | -0.026 |
opes | -0.025 |
ths | -0.024 |
iously | -0.024 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ulu | +0.045 |
ory | +0.042 |
J | +0.041 |
common | +0.039 |
ola | +0.038 |
Neg logit contributions | |
oved | -0.046 |
opes | -0.043 |
zed | -0.043 |
sed | -0.040 |
erved | -0.040 |
Token | L |
Token ID | 43 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ory | +0.008 |
ulu | +0.008 |
common | +0.007 |
J | +0.007 |
Jill | +0.007 |
Neg logit contributions | |
oved | -0.006 |
zed | -0.006 |
opes | -0.006 |
Leave | -0.005 |
chair | -0.005 |
Token | ily |
Token ID | 813 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
common | +0.032 |
mer | +0.031 |
ulu | +0.030 |
mineral | +0.030 |
ory | +0.029 |
Neg logit contributions | |
oved | -0.046 |
opes | -0.043 |
zed | -0.043 |
erved | -0.040 |
iously | -0.040 |
Token | did |
Token ID | 750 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
ulu | +0.018 |
ory | +0.017 |
J | +0.017 |
Jill | +0.016 |
common | +0.015 |
Neg logit contributions | |
oved | -0.026 |
zed | -0.025 |
opes | -0.025 |
ths | -0.024 |
iously | -0.024 |
Token | not |
Token ID | 407 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
oved | +0.004 |
opes | +0.004 |
ths | +0.004 |
zed | +0.004 |
iously | +0.004 |
Neg logit contributions | |
J | -0.002 |
ulu | -0.002 |
ory | -0.002 |
Jill | -0.002 |
common | -0.002 |
Token | like |
Token ID | 588 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
oved | +0.005 |
zed | +0.005 |
opes | +0.004 |
erved | +0.004 |
ths | +0.004 |
Neg logit contributions | |
ulu | -0.004 |
ory | -0.004 |
J | -0.004 |
ola | -0.003 |
ora | -0.003 |
Token | school |
Token ID | 1524 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
ulu | +0.011 |
J | +0.011 |
ory | +0.011 |
Jill | +0.010 |
common | +0.010 |
Neg logit contributions | |
oved | -0.010 |
zed | -0.010 |
opes | -0.010 |
ths | -0.009 |
iously | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
zed | +0.017 |
opes | +0.017 |
oved | +0.017 |
iously | +0.016 |
sed | +0.016 |
Neg logit contributions | |
J | -0.009 |
ulu | -0.009 |
ory | -0.009 |
Jill | -0.008 |
common | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
oved | +0.001 |
opes | +0.000 |
zed | +0.000 |
meanings | +0.000 |
iously | +0.000 |
Neg logit contributions | |
ulu | -0.001 |
ory | -0.001 |
J | -0.001 |
common | -0.001 |
mer | -0.001 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
oved | +0.033 |
zed | +0.031 |
opes | +0.031 |
ths | +0.029 |
iously | +0.029 |
Neg logit contributions | |
ulu | -0.034 |
ory | -0.033 |
J | -0.033 |
common | -0.030 |
Jill | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ory | +0.060 |
ulu | +0.060 |
Jill | +0.059 |
J | +0.058 |
Jenny | +0.057 |
Neg logit contributions | |
oved | -0.075 |
zed | -0.074 |
opes | -0.072 |
ths | -0.069 |
iously | -0.066 |
Token | pack |
Token ID | 2353 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
zed | +0.005 |
oved | +0.005 |
ze | +0.005 |
opes | +0.005 |
zy | +0.004 |
Neg logit contributions | |
ory | -0.005 |
J | -0.005 |
ulu | -0.005 |
ora | -0.004 |
common | -0.004 |
Token | your |
Token ID | 534 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ulu | +0.007 |
J | +0.007 |
ory | +0.007 |
common | +0.006 |
ora | +0.006 |
Neg logit contributions | |
oved | -0.007 |
zed | -0.007 |
opes | -0.007 |
iously | -0.007 |
ths | -0.007 |
Token | backpack |
Token ID | 22526 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ulu | +0.009 |
ory | +0.009 |
J | +0.009 |
common | +0.008 |
Jill | +0.008 |
Neg logit contributions | |
oved | -0.013 |
zed | -0.013 |
opes | -0.013 |
ths | -0.012 |
iously | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
oved | +0.062 |
zed | +0.061 |
opes | +0.060 |
ths | +0.057 |
iously | +0.056 |
Neg logit contributions | |
ulu | -0.043 |
ory | -0.042 |
J | -0.042 |
Jill | -0.039 |
common | -0.038 |
Token | school |
Token ID | 1524 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
oved | +0.079 |
zed | +0.076 |
opes | +0.076 |
ths | +0.072 |
iously | +0.071 |
Neg logit contributions | |
ulu | -0.053 |
J | -0.051 |
ory | -0.051 |
common | -0.047 |
Jill | -0.046 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
oved | +0.000 |
zed | +0.000 |
opes | +0.000 |
ths | +0.000 |
iously | +0.000 |
Neg logit contributions | |
ulu | -0.000 |
ory | -0.000 |
J | -0.000 |
common | -0.000 |
Jill | -0.000 |
Token | ," |
Token ID | 553 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
oved | +0.004 |
zed | +0.004 |
opes | +0.004 |
ths | +0.003 |
iously | +0.003 |
Neg logit contributions | |
ulu | -0.003 |
ory | -0.003 |
J | -0.003 |
common | -0.002 |
Jill | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
oved | +0.011 |
opes | +0.011 |
zed | +0.011 |
iously | +0.010 |
ths | +0.010 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
ory | -0.006 |
Jill | -0.006 |
common | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
oved | +0.011 |
zed | +0.011 |
opes | +0.011 |
iously | +0.011 |
ths | +0.010 |
Neg logit contributions | |
ulu | -0.006 |
J | -0.006 |
ory | -0.006 |
Jill | -0.005 |
common | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
oved | +0.013 |
zed | +0.012 |
opes | +0.012 |
ths | +0.012 |
iously | +0.012 |
Neg logit contributions | |
ulu | -0.007 |
J | -0.006 |
ory | -0.006 |
Jill | -0.006 |
common | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ulu | +0.038 |
ory | +0.036 |
J | +0.034 |
common | +0.034 |
ora | +0.033 |
Neg logit contributions | |
oved | -0.028 |
zed | -0.026 |
der | -0.025 |
opes | -0.025 |
sed | -0.024 |
Token | said |
Token ID | 531 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
ulu | +0.028 |
ory | +0.027 |
J | +0.027 |
common | +0.025 |
Jill | +0.024 |
Neg logit contributions | |
oved | -0.044 |
zed | -0.042 |
opes | -0.042 |
ths | -0.040 |
sed | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
ulu | +0.026 |
J | +0.025 |
ory | +0.025 |
common | +0.023 |
Jill | +0.022 |
Neg logit contributions | |
oved | -0.032 |
zed | -0.031 |
opes | -0.030 |
iously | -0.028 |
ths | -0.028 |
Token | " |
Token ID | 366 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
ulu | +0.002 |
J | +0.002 |
ory | +0.002 |
Jill | +0.002 |
common | +0.002 |
Neg logit contributions | |
oved | -0.002 |
opes | -0.002 |
zed | -0.002 |
ths | -0.002 |
iously | -0.002 |
Token | My |
Token ID | 3666 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
oved | +0.033 |
zed | +0.031 |
opes | +0.031 |
ths | +0.029 |
iously | +0.028 |
Neg logit contributions | |
ulu | -0.034 |
ory | -0.034 |
J | -0.031 |
Jill | -0.031 |
common | -0.030 |
Token | shadow |
Token ID | 9082 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
ulu | +0.016 |
J | +0.016 |
ory | +0.016 |
common | +0.015 |
Jill | +0.015 |
Neg logit contributions | |
oved | -0.018 |
zed | -0.017 |
opes | -0.017 |
ths | -0.016 |
iously | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
oved | +0.111 |
zed | +0.108 |
opes | +0.105 |
ths | +0.101 |
iously | +0.100 |
Neg logit contributions | |
ulu | -0.089 |
ory | -0.085 |
J | -0.084 |
common | -0.080 |
Jill | -0.080 |
Token | different |
Token ID | 1180 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ory | +0.039 |
ulu | +0.038 |
J | +0.038 |
ora | +0.034 |
ola | +0.034 |
Neg logit contributions | |
oved | -0.035 |
opes | -0.033 |
zed | -0.033 |
sed | -0.031 |
ths | -0.030 |
Token | because |
Token ID | 780 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ulu | +0.030 |
J | +0.029 |
ory | +0.029 |
common | +0.026 |
Jill | +0.026 |
Neg logit contributions | |
oved | -0.039 |
opes | -0.037 |
zed | -0.037 |
iously | -0.035 |
ths | -0.034 |
Token | I |
Token ID | 314 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
oved | +0.010 |
zed | +0.010 |
opes | +0.010 |
ths | +0.009 |
iously | +0.009 |
Neg logit contributions | |
ory | -0.007 |
ulu | -0.007 |
J | -0.007 |
common | -0.006 |
ora | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
J | +0.050 |
ulu | +0.050 |
ory | +0.048 |
Jill | +0.044 |
ola | +0.043 |
Neg logit contributions | |
oved | -0.052 |
zed | -0.049 |
opes | -0.048 |
sed | -0.046 |
meanings | -0.044 |
Token | for |
Token ID | 329 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
oved | +0.046 |
opes | +0.044 |
zed | +0.043 |
sed | +0.042 |
ths | +0.041 |
Neg logit contributions | |
ulu | -0.035 |
J | -0.035 |
ory | -0.033 |
common | -0.031 |
Jill | -0.030 |
Token | Emma |
Token ID | 18966 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
zed | +0.072 |
oved | +0.071 |
opes | +0.071 |
ths | +0.065 |
iously | +0.065 |
Neg logit contributions | |
ulu | -0.066 |
J | -0.062 |
ory | -0.062 |
common | -0.059 |
ora | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ulu | +0.003 |
J | +0.003 |
ory | +0.003 |
common | +0.002 |
Jill | +0.002 |
Neg logit contributions | |
oved | -0.003 |
zed | -0.003 |
opes | -0.003 |
iously | -0.003 |
ths | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ulu | +0.005 |
J | +0.005 |
ory | +0.004 |
common | +0.004 |
ola | +0.004 |
Neg logit contributions | |
zed | -0.006 |
oved | -0.006 |
opes | -0.006 |
ths | -0.006 |
iously | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
oved | +0.044 |
zed | +0.043 |
opes | +0.042 |
ths | +0.040 |
iously | +0.040 |
Neg logit contributions | |
ulu | -0.036 |
ory | -0.035 |
J | -0.035 |
Jill | -0.032 |
common | -0.032 |
Token | brother |
Token ID | 3956 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
oved | +0.007 |
opes | +0.006 |
zed | +0.006 |
sed | +0.006 |
iously | +0.006 |
Neg logit contributions | |
ulu | -0.005 |
J | -0.005 |
ory | -0.005 |
common | -0.005 |
ola | -0.004 |
Token | Tom |
Token ID | 4186 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
oved | +0.102 |
zed | +0.097 |
opes | +0.093 |
iously | +0.088 |
ths | +0.086 |
Neg logit contributions | |
ulu | -0.091 |
J | -0.083 |
ory | -0.081 |
common | -0.081 |
ola | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ulu | +0.000 |
J | +0.000 |
ory | +0.000 |
common | +0.000 |
ora | +0.000 |
Neg logit contributions | |
oved | -0.000 |
zed | -0.000 |
opes | -0.000 |
iously | -0.000 |
aged | -0.000 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
oved | +0.005 |
opes | +0.005 |
zed | +0.005 |
sed | +0.004 |
iously | +0.004 |
Neg logit contributions | |
ulu | -0.004 |
J | -0.004 |
ory | -0.004 |
common | -0.004 |
ola | -0.004 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
ulu | +0.050 |
J | +0.048 |
ory | +0.047 |
common | +0.044 |
Jill | +0.043 |
Neg logit contributions | |
oved | -0.043 |
opes | -0.041 |
zed | -0.041 |
sed | -0.038 |
ths | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
opes | +0.003 |
oved | +0.003 |
zed | +0.003 |
ow | +0.003 |
sed | +0.003 |
Neg logit contributions | |
ulu | -0.003 |
ory | -0.003 |
J | -0.003 |
ora | -0.003 |
common | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
zed | +0.004 |
oved | +0.004 |
opes | +0.003 |
ths | +0.003 |
iously | +0.003 |
Neg logit contributions | |
ulu | -0.003 |
J | -0.003 |
ory | -0.003 |
common | -0.003 |
rust | -0.003 |
Token | hopefully |
Token ID | 11481 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
zed | +0.016 |
oved | +0.016 |
opes | +0.016 |
ths | +0.015 |
iously | +0.015 |
Neg logit contributions | |
ulu | -0.014 |
J | -0.014 |
ory | -0.014 |
common | -0.013 |
Jill | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ulu | +0.008 |
J | +0.007 |
ory | +0.007 |
common | +0.006 |
ola | +0.006 |
Neg logit contributions | |
oved | -0.009 |
zed | -0.009 |
opes | -0.008 |
iously | -0.008 |
ths | -0.008 |
Token | â |
Token ID | 22940 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
J | +0.048 |
ulu | +0.046 |
ory | +0.044 |
Jill | +0.042 |
common | +0.041 |
Neg logit contributions | |
oved | -0.055 |
zed | -0.052 |
opes | -0.051 |
iously | -0.048 |
ths | -0.048 |
Token | € |
Token ID | 26391 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ulu | +0.001 |
ory | +0.001 |
J | +0.001 |
common | +0.001 |
Jill | +0.001 |
Neg logit contributions | |
oved | -0.001 |
zed | -0.001 |
opes | -0.001 |
ths | -0.001 |
iously | -0.001 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
oved | +0.047 |
opes | +0.044 |
zed | +0.043 |
iously | +0.043 |
der | +0.040 |
Neg logit contributions | |
J | -0.054 |
ory | -0.051 |
ulu | -0.051 |
Jill | -0.051 |
Jenny | -0.049 |
Token | ll |
Token ID | 297 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
oved | +0.166 |
zed | +0.158 |
opes | +0.154 |
iously | +0.147 |
ths | +0.145 |
Neg logit contributions | |
ulu | -0.107 |
ory | -0.105 |
J | -0.105 |
common | -0.102 |
Jill | -0.094 |
Token | see |
Token ID | 766 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
J | +0.003 |
ulu | +0.003 |
ory | +0.003 |
common | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
oved | -0.004 |
zed | -0.004 |
opes | -0.004 |
iously | -0.004 |
erved | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
oved | +0.001 |
zed | +0.001 |
opes | +0.001 |
ths | +0.001 |
iously | +0.001 |
Neg logit contributions | |
ulu | -0.000 |
J | -0.000 |
ory | -0.000 |
Jill | -0.000 |
common | -0.000 |
Token | purple |
Token ID | 14032 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ulu | +0.020 |
J | +0.019 |
ory | +0.018 |
ola | +0.017 |
Jill | +0.017 |
Neg logit contributions | |
oved | -0.017 |
ths | -0.017 |
zed | -0.017 |
ow | -0.016 |
sed | -0.016 |
Token | sunset |
Token ID | 26428 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
ulu | +0.007 |
J | +0.006 |
ory | +0.006 |
common | +0.006 |
Jill | +0.006 |
Neg logit contributions | |
oved | -0.008 |
zed | -0.008 |
opes | -0.008 |
iously | -0.007 |
ths | -0.007 |
Token | took |
Token ID | 1718 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
oved | +0.047 |
opes | +0.045 |
zed | +0.045 |
iously | +0.042 |
ths | +0.042 |
Neg logit contributions | |
ulu | -0.036 |
ory | -0.035 |
J | -0.035 |
Jill | -0.033 |
common | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
zed | +0.008 |
oved | +0.008 |
opes | +0.008 |
iously | +0.008 |
ths | +0.007 |
Neg logit contributions | |
ulu | -0.008 |
ory | -0.007 |
J | -0.007 |
common | -0.007 |
ora | -0.006 |
Token | friend |
Token ID | 1545 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
oved | +0.030 |
zed | +0.029 |
opes | +0.028 |
ths | +0.027 |
iously | +0.026 |
Neg logit contributions | |
ulu | -0.022 |
ory | -0.021 |
J | -0.021 |
common | -0.020 |
Jill | -0.020 |
Token | â |
Token ID | 22940 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
oved | +0.017 |
zed | +0.017 |
opes | +0.017 |
ths | +0.016 |
iously | +0.015 |
Neg logit contributions | |
ulu | -0.017 |
ory | -0.017 |
J | -0.017 |
Jill | -0.016 |
common | -0.016 |
Token | € |
Token ID | 26391 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ulu | +0.013 |
J | +0.012 |
ory | +0.012 |
common | +0.012 |
Jill | +0.012 |
Neg logit contributions | |
oved | -0.010 |
zed | -0.010 |
opes | -0.009 |
iously | -0.009 |
ths | -0.009 |
Token | ™ |
Token ID | 8151 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
oved | +0.027 |
opes | +0.026 |
zed | +0.025 |
iously | +0.024 |
ths | +0.023 |
Neg logit contributions | |
J | -0.041 |
ory | -0.039 |
ulu | -0.039 |
Jill | -0.038 |
common | -0.037 |
Token | s |
Token ID | 82 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
oved | +0.127 |
zed | +0.120 |
opes | +0.117 |
iously | +0.111 |
ths | +0.110 |
Neg logit contributions | |
ulu | -0.111 |
J | -0.107 |
ory | -0.107 |
common | -0.102 |
Jill | -0.097 |
Token | advice |
Token ID | 5608 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ulu | +0.006 |
J | +0.006 |
ory | +0.006 |
Jill | +0.006 |
common | +0.006 |
Neg logit contributions | |
oved | -0.007 |
zed | -0.007 |
opes | -0.007 |
ths | -0.006 |
iously | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ulu | +0.003 |
J | +0.003 |
ory | +0.003 |
common | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
oved | -0.005 |
zed | -0.005 |
opes | -0.005 |
ths | -0.004 |
iously | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
oved | +0.000 |
zed | +0.000 |
opes | +0.000 |
iously | +0.000 |
ths | +0.000 |
Neg logit contributions | |
ulu | -0.001 |
J | -0.001 |
ory | -0.001 |
common | -0.001 |
mer | -0.000 |
Token | stayed |
Token ID | 9658 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
oved | +0.011 |
zed | +0.011 |
opes | +0.011 |
iously | +0.010 |
ths | +0.010 |
Neg logit contributions | |
ulu | -0.008 |
ory | -0.007 |
J | -0.007 |
common | -0.007 |
Jill | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
oved | +0.027 |
zed | +0.026 |
opes | +0.026 |
iously | +0.024 |
ths | +0.024 |
Neg logit contributions | |
ulu | -0.031 |
ory | -0.029 |
J | -0.029 |
common | -0.028 |
ora | -0.026 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
oved | +0.034 |
zed | +0.033 |
opes | +0.032 |
ths | +0.030 |
iously | +0.030 |
Neg logit contributions | |
ulu | -0.027 |
J | -0.026 |
ory | -0.026 |
Jill | -0.024 |
common | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
oved | +0.070 |
zed | +0.068 |
opes | +0.066 |
ths | +0.063 |
iously | +0.062 |
Neg logit contributions | |
ulu | -0.080 |
ory | -0.078 |
J | -0.077 |
common | -0.072 |
Jill | -0.071 |
Token | all |
Token ID | 477 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
ulu | +0.011 |
ory | +0.011 |
J | +0.010 |
common | +0.009 |
ora | +0.009 |
Neg logit contributions | |
oved | -0.015 |
zed | -0.015 |
opes | -0.014 |
ths | -0.014 |
iously | -0.013 |
Token | his |
Token ID | 465 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ulu | +0.002 |
J | +0.002 |
ory | +0.001 |
Jill | +0.001 |
common | +0.001 |
Neg logit contributions | |
oved | -0.003 |
zed | -0.003 |
opes | -0.003 |
iously | -0.003 |
ths | -0.003 |
Token | hard |
Token ID | 1327 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
oved | +0.072 |
zed | +0.069 |
opes | +0.068 |
iously | +0.064 |
ths | +0.064 |
Neg logit contributions | |
ulu | -0.061 |
ory | -0.060 |
J | -0.060 |
common | -0.058 |
Jill | -0.056 |
Token | work |
Token ID | 670 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
oved | +0.108 |
zed | +0.104 |
opes | +0.103 |
ths | +0.097 |
iously | +0.097 |
Neg logit contributions | |
ulu | -0.071 |
ory | -0.070 |
J | -0.069 |
common | -0.065 |
Jill | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
oved | +0.008 |
opes | +0.008 |
zed | +0.008 |
iously | +0.008 |
ths | +0.008 |
Neg logit contributions | |
ulu | -0.007 |
J | -0.007 |
ory | -0.007 |
common | -0.006 |
Jill | -0.006 |
Token | practice |
Token ID | 3357 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
oved | +0.024 |
zed | +0.023 |
opes | +0.023 |
ths | +0.022 |
iously | +0.022 |
Neg logit contributions | |
ulu | -0.019 |
J | -0.019 |
ory | -0.019 |
common | -0.017 |
Jill | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ulu | +0.036 |
J | +0.035 |
ory | +0.035 |
common | +0.033 |
Jill | +0.033 |
Neg logit contributions | |
oved | -0.043 |
zed | -0.041 |
opes | -0.041 |
iously | -0.039 |
ths | -0.038 |
Token | creativity |
Token ID | 16389 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
ulu | +0.005 |
ory | +0.005 |
J | +0.005 |
common | +0.004 |
Jill | +0.004 |
Neg logit contributions | |
oved | -0.005 |
zed | -0.005 |
opes | -0.005 |
ths | -0.005 |
iously | -0.005 |